Summary of health statistics test questions

best multiple choice question

1. The method of collecting information is: E

A. Collect various reports B. Collect various work records C. Conduct special investigations

D. Conduct scientific experiments E. All of the above are true

2. The basic steps of statistical work are: D

A. Investigate data, review data, organize data B. Collect data, review data, analyze data

C. Investigate data, organize data, and analyze data D. Collect data, organize data, and analyze data

E. All of the above are correct

3. In a sampling study the sample is: D

A. Part of the whole B. Any part of the whole C. Typical part of the whole

D. A representative part of the population E. A meaningful part of the population

4. The relationship between measurement data, counting data and grade data is: C

A. Measurement data has some properties of both counting data and grade data.

B. Counting data has some properties of both measurement data and grade data.

C. Grade data have some properties of both measurement data and counting data

D. Counting data has some properties of measurement data

E.None of the above

5. Use a graph to represent the rate of increase and decrease in the incidence of three diseases in each year since the liberation of a certain place. It is appropriate to draw D:

A. Ordinary line graph B. Histogram C. Composition ratio bar graph D. Semi-logarithmic line graph E. Bar graph

6. Histograms can be used for:

A. The internal composition of a certain phenomenon B. Comparison of various phenomena C. Comparison of a certain phenomenon

D. Frequency distribution of a certain phenomenon E. Development speed of a certain phenomenon

7. The requirements for statistical charts are:

A. Simple and clear B. Clear hierarchy C. Explain the problem clearly D. Avoid bloat and complexity E. All of the above are true

8. When making a frequency table, the number of groups is generally:

A.5-10 B.8-15 C.10-30 D.15-20 E.＞20

9.As a statistical indicator, the average is used to analyze:

A. Count data B. Measurement data C. Grade grouping data D. Survey data

E. None of the above are correct

10. Commonly used indicators indicating the variation of variable values are:

A.Full range B.Standard deviation C.Variance D.Coefficient of variation E.All of the above

11. When determining the normal value range of a certain indicator for normal people, the objects of investigation are:

A. People who have never been sick B. People who have met the health requirements C. People who exclude diseases and factors that affect the research indicators D. People who have only suffered from minor illnesses but do not affect the research indicators E. People who have been excluded A certain disease or a person who has been exposed to a certain factor

12. Standard error:

A. Inversely proportional to the standard deviation B. Directly proportional to the standard deviation C. Inversely proportional to the square of the standard deviation

D. Proportional to the square of the standard deviation E. None of the above are correct

13. refers to:

A. The degree of dispersion of all observed values from the population mean B. The degree of dispersion of a certain sample mean

C. The degree of dispersion of all sample means from the population mean D. The degree of dispersion of some sample means from the population mean

E. The degree of dispersion of all sample means with the same content to the population mean

14. Express:

A.95% normal value range B.95% confidence interval C.99% normal value range

D. 99% confidence interval E. None of the above is correct

15. The composition ratio is usually based on which of the following indicators is the base of the ratio:

A.100% B.1000‰ C.10000/10,000 D.100000/100,000 E. It depends on the specific situation

16. The sum of the relative numbers of each constituent part of a thing should be:

A. Greater than 1 B. Less than 1 C. Equal to 1 D. Not necessarily E. None of the above are correct

17. Under the normal curve, the area from –∞ to on the horizontal axis is ( )

A. 95% B. 45% C. 97.5% D. 47.5% E. Not sure

18. The data used for statistical analysis must be ( )

A. Complete, accurate and timely B. Randomly obtained C. Meet the same conditions D. Sufficient quantity E. All of the above are correct

19. Indicate which indicator of the following variables is a statistic

A. B. C.μ D.π E.b

20. The applicable formula for calculating the sampling error of the sample rate is:

A. B. C. D.

E. None of the above are correct

21.The degrees of freedom for the test of the R×C table are:

A. B. C. D. E.

22.The basic principles of experimental design are

A. Principle of sameness B. Principle of randomness C. Principle of comparison D. Principle of repetition E. All of the above

23. In related analysis:

A. The closer it is to 1, the more concentrated the scatter plot is. B. The closer it is to 0, the more concentrated the scatter plot is.

C., the more concentrated the scatter plot is. D., the more concentrated the scatter plot is. E. None of the above are correct.

24. If it is known, there must be:

A. B. C. D. E.

25. The main contents of relevant analysis include:

A. Determine the quantitative relationship between variables B. Determine whether there is a relationship between variables C. Determine whether there is a causal relationship between variables

D. Determine the closeness of the relationship between variables E. None of the above

26. In the paired rank sum test, there are 8 pairs of data, and there is no 0 in the difference, then:

A. -3 B.9 C.-9 D.-27 E.30

27. The basic idea of the rank sum test for paired comparisons is: if the hypothesis test is established, then for the sample:

A. The absolute value of the positive rank sum is greater than the absolute value of the negative rank sum.

B. The absolute value of the positive rank sum is smaller than the absolute value of the negative rank sum.

C. The absolute value of the positive rank sum will not differ greatly from the absolute value of the negative rank sum.

D. The absolute value of the positive rank sum is equal to the absolute value of the negative rank sum.

E. The absolute value of positive rank sum is very different from the absolute value of negative rank sum.

28. In the rank sum test for comparing two samples in a group design, there are two minimum data in group A (0.2, 0.2), and there are also two minimum data in group B (0.2, 0.2). Then the rank of the data 0.2 is :

A.2 B.3 C.4.5 D.2.5 E.3.5

29. When the second type error β changes from 0.2 to 0.3, then the first type error α is:

A. Increase B. Decrease C. Uncertain D. No change E. None of the above

30.Except which of the following indicators are statistical indicators of disease:

A. Cure rate B. Fatality rate of a certain disease C. Death rate of a certain disease D. Infection rate E. Incidence rate

31． To calculate the average level of a certain antibody titer, it is generally appropriate to choose ( )

A. Arithmetic mean B. Geometric mean C. Median D. Percentile E. Range

32. The content of statistical inference ( )

A. It is to use sample indicators to estimate the corresponding overall indicators. B. It is to test statistical "hypotheses".

C. Estimated normal value range D. Neither A nor B

E, A, B are all

33. The appropriate index to use to compare the degree of variation in height and weight is ( )

A. Standard deviation B. Standard error C. Interquartile range D. Coefficient of variation E. Full range

34. The average of observation values 2, 5, 10, 7, 9, 8, 20, 100 is ( )

A、20.14 B、6.15 C、8.5 D、 20 E、10

35． When n is constant, when the second type error β changes from 0.2 to 0.3, the first type error ( )

A. Increase B. Decrease C. Uncertain D. No change E. None of the above are correct

36. Hypothesis testing for comparing measurement data of two small samples should first consider ( )

A. Use test B. Use test C. Use rank sum test D. Whether the data meets the conditions of test or rank sum test E. Choose any test method

37. Sampling error refers to ( )

A. The difference between individual values and population values B. The difference between sample statistics and between sample statistics and population parameter values

C. The difference between the individual value and the statistical value D. The difference between the overall parameter value and the overall parameter value E. None of the above is correct

38． Perform linear correlation and regression analysis on the same bivariate data, there are ( )

A、 B、 C、 D、

E. It has nothing to do with the sign of

39. Which of the following data characteristics can be fully described using mean and standard deviation ( )

A. Positive skew distribution B. Negative skew distribution C. Normal distribution D. Asymmetric distribution

40． Comparing the four sample rates, it can be considered as ( )

The population rates are not equal or not equal. B. The population rates are not equal. C. The sample rates are not equal.

D. The sample rates are not equal or not equal. E. The population rates are equal.

2. Fill in the blanks

1. The basic steps of statistical work are ( ), ( ), ( ).

2. The structure of the statistical table is mainly composed of ( ), ( ), ( ) and ( ).

3. The average mainly includes ( ), ( ) and ( ).

4. Statistical data can be divided into three types: ( ), ( ) and ( ).

5. The ( ) graph can describe the tendency of one thing to change with another thing, and the ( ) graph to describe the speed of one thing changing with another thing.

6. Use ( ) and ( ) to comprehensively describe the characteristics of skewed distribution measurement data.

7. The two characteristics of frequency distribution are ( ) and ( )

3. True or False Questions

1. It is appropriate to use standard deviation to compare the degree of variation in height and weight of a group of children. ( )

2. Histograms can be used to reflect the birth weight distribution of a batch of newborns. ( )

3． If the prevalence rates of a certain disease in a certain area for three consecutive years are 6.0%, 9.0%, and 12.0%, then the total prevalence rate of the disease in three years is: (6.0+9.0+12.0)/3=9.0%. ( )

4. As the sample size of a sampling study increases, the standard error of the mean becomes smaller. ( )

5. When the degrees of freedom tend to infinity, the t distribution is the standard normal distribution. ( )

6. The purpose of the t test for comparing the means of two samples is to test whether the difference between the means of the two samples is equal to 0. ( )

7. The χ2 test can be used to compare the means of two samples. ( )

8. Linear correlation reflects the linear relationship between two variables. ( )

9. Correlation must be causation. ( )

10. If the t-test result is to reject H0, the smaller the P value, the greater the difference between the two population means. ( )

4. Short answer questions

1. When measuring standardized rates, what is usually used as the standard population?

2. What are the methods for calculating reference value ranges?

3． Briefly describe the application conditions of non-parametric tests.

4. To which materials does level correlation apply specifically?

5. Calculation questions

1. A large number of studies have shown that the average biparietal diameter of full-term normal male Han newborns before delivery is 9.3cm. A doctor recorded the prepartum biparietal diameter (cm) of 12 Han full-term male newborns in a mountainous area as follows:

9.95 9.33 9.49 9.00 10.09 9.15 9.52 9.33 9.16 9.37 9.11 9.27

I would like to ask whether the prepartum biparietal diameter of male newborns in this mountainous area is equal to that of ordinary newborns? (Assume the test statistic is 1.026)

2. The red blood cell count of 360 healthy adult men was sampled in a certain place. The mean was 4.66 and the standard deviation was 0.58. Is there any difference between the red blood cell count of men in this place and the standard value of 4.84? (Assume the test statistic is 5.89)

3． In order to compare the white blood cell count of earlobe blood and finger blood, the researchers surveyed 8 adults and took earlobe blood and finger blood at the same time, as shown in the table below.

Number: 1 2 3 4 5 6 7 8

Earlobe blood: 9.7 6.2 7.0 5.3 8.1 9.9 4.7 5.8

Finger blood: 6.7 5.4 5.0 7.5 8.3 4.6 4.2 7.5

Question: (1) If the data follows a normal distribution, try to compare whether the white blood cell counts of the two are the same? (Assume the test statistic is 1.073)

(2) If the data does not obey the normal distribution, try to compare whether the white blood cell counts of the two are the same?

4. The determination of urinary lead used to use the wet thermal digestion method-dithiourea method, and later the nitric acid-potassium permanganate cold digestion method was used. The data are as follows:

patient number

Cold method

0.50

0.60

0.34

0.57

0.22

0.67

0.16

0.76

0.08

Thermal method

0.58

0.33

0.63

0.38

0.39

0.30

0.71

0.19

0.79

0.08

Question: (1) If the data obeys a normal distribution, try to compare the results obtained by the two methods. Is there any difference? (Assume the test statistic is 0.067)

(2) If the data does not obey the normal distribution, try to compare the results obtained by the two methods. Is there any difference?

5. A doctor used two therapies to treat cerebral vascular infarction. The results are shown in the table below. Try to compare whether the curative effects of the two therapies are the same? (Hypothesis test statistic is 0.595) (10 points)

Effects of two therapies on cerebral infarction

Number of people treated with therapy Number of effective cases Effective rate (%)

A therapy 31 25 80.65

Treatment B 32 29 90.63

6. In order to understand the English proficiency of students majoring in health management at medical schools A and B, 108 people were randomly selected to take a standard test. The results are shown in the table below. Is there any difference in the English standard meeting rates of students majoring in health management between the two medical schools? (Assume the test statistic is 5.526)

English Compliance Rate of Health Management Students from Two Medical Colleges

medical school

Number of people who meet the target

Number of people taking the exam

Compliance rate(%)

First

71.4

Second

48.5

A. mean unchanged

B. Standard deviation remains unchanged

C. Both change

D． Both remain unchanged

Each observation value is added (or subtracted) at the same time by a certain constant B

Each observation value is multiplied (or divided) by a certain constant C at the same time

Using the coefficient of variation to compare the degree of variation is suitable for

1. Different indicators have large differences in mean values.

2. Different indicators have large differences in standard deviations

3． The same indicator, the mean difference is large

4. The same indicators, but the standard difference is quite different

Overview of medical statistical methods
l. The population mentioned in statistics refers to: A
AThe whole group of homogeneous research objects determined according to the research purpose
BThe whole group of randomly imagined research objects A Statistical design B Collecting data C Organizing data D Analyzing data E None of the above are incorrect Number of patients treated: 8 23 6 3 1 D any part E a typical part A a valuable part B a meaningful part C a representative part 6. The sample is the population C A counting data B measurement data C unordered classification data D ordered classification data E numerical variable data The type of data is: D Treatment results: Cured, significantly improved, worsened, and died. 5. A new therapy treated 41 patients with a certain disease. The treatment results are as follows: A counting data B measurement data C grade data D classification data E ordered classification data 4. The original data for measuring height, weight and other indicators are called: B A Stratified sampling B Systematic sampling C Cluster sampling D Simple random sampling E Two-level sampling 3. The method of drawing lots belongs to D D A certain event will happen The possibility is very high E None of the above are correct A A certain event will definitely happen B A certain event will definitely not happen C A certain event is very unlikely to happen 2. Probability P=0, it means B E Research divided by population All objects D All research subjects divided by time
C All research subjects divided by region A collecting data, designing, organizing data, analyzing data B collecting data, organizing data, designing, statistical inference C design , collect data, organize data, analyze data D collect data, organize data, check and analyze data　　 E collect data, organize data, analyze data and make inferences 9. Good experimental design can reduce manpower and material resources and improve experimental efficiency; it can also help eliminate or reduce: B A sampling error B systematic error C random error D liability accident E none of the above D Exclude people who have suffered from a certain disease or been exposed to a certain factor E None of the above C People who have only suffered from mild diseases, but it does not affect the indicators being studied A People who have never been sick B People who exclude diseases and factors that affect the research indicators 19. When determining the normal range of a certain indicator for normal people, the subjects of the investigation are B Frequency distribution with mean E as center C. A frequency distribution centered on variable D Number of observations Frequency distribution with center E A t value B. A frequency distribution centered on parameter 18. The normal distribution is a frequency distribution centered on E E. None of the above are true. C Sample The sampling error may be larger. D. The representativeness of the sample to the population may be worse. A The greater the variation among observed individuals B The smaller the variation among observed individuals 17. The meaning of the larger standard deviation. Which of the following concepts is wrong? B D μ±t0.05, υSX E X±2.58S A X±1.96S B X±1.96SX C μ±1.96SX 16. Which of the following formulas can be used to estimate the medical 95% normal range A A Full distance B Standard deviation C Variance D Coefficient of variation E Range 15. To compare the degree of height variation between a 12-year-old boy and an 18-year-old man, the indicators that should be used are: D A 5 B 5．5 C 6 D lO E 12 Ask the average number of food poisoning How many hours is the incubation period? C 14. Food poisoning occurred in a factory. The incubation periods of 9 patients were: 16, 2, 6, 3, 30, 2, 10, 2, 24+ (hours). CNeither of them changes D Both of them changeENone of the above is correct A The mean remains unchanged and the standard deviation changes B The mean changes and the standard deviation remains unchanged 13. After adding (or subtracting) the same number to each observation value: B A X B G C M D S E CV 12. The distribution nature of certain measurement data is unknown. To calculate the central tendency index, it is appropriate to choose C A Arithmetic mean B Geometric mean C Median D Range E Rate 11. Indicates the most common calculation of the average level of serological titer data B Chapter 8 Statistical description of numerical variable data D The principle of crossover E None of the above A The principle of control B The principle of randomization C The principle of repetition 10． Which of the following is not a principle that should be followed in experimental design D A. The larger the standard deviation, the more representative the mean is. B. The smaller the standard deviation, the less representative the mean is. C The larger the mean, the smaller the standard deviation D The larger the mean, the larger the standard deviation E The smaller the standard deviation, the more representative the mean Chapter 9 Statistical Inference of Numerical Variable Data 21. A sample is drawn from a population. The reason for sampling error is A A. There is variation among individuals in the population. B. Sampling does not follow the randomization principle. C. The individuals are not homogeneous D There are few individuals making up the sample E The grouping is unreasonable 22. In the t test comparing the means of the two samples, the result is P<0.05, which is statistically significant. The smaller P is, then E A means that the difference between the means of the two samples is greater. B means that the difference between the means of the two populations is greater. C means that the sample mean and the population mean are bigger The greater the difference D, the more reason there is to believe that the means of the two samples are different E The more reason there is to believe that the means of the two populations are different 23. A paired t test is performed on data composed of 10 pairs (20 data), and its degrees of freedom are equal to C A 10 B 20 C 9 D 18 E 19 24 ． The t test result, P>0.05, can be considered as B A There is no significant difference in the means of the two populations B There is no significant difference in the means of the two samples C The two populations The difference in means is significant D The difference in means of the two samples is significant E None of the above is correct 25. Which of the following is not a note of the t test D A The data should be comparable B Don’t make the conclusion absolute C Choose the appropriate test method based on the data D The denominator E should not be too small and the data should obey the normal distribution

26. In a sampling study, when the sample size gradually increases B
A The standard deviation gradually decreases B The standard error gradually decreases C The standard deviation gradually increases
D The standard error gradually increases E Both the standard deviation and the standard error gradually increase
27. t
A is the mean of the two populations, the difference is not significant, B is the mean of the two populations, the difference is significant E None of the above 28. In the t test of two sample means, the test hypothesis (H0) is B A μ1≠μ2 B μ1=μ2 C X1≠X2 D X1=X2 E X1=X2< a i=9> 29. Among two samples from the same population, which of the following indicators has a small value and its sample mean is more reliable in estimating the population mean? A A. Sx B .S C .x D .CV E S2 30. The relationship between standard deviation and standard error is: C A The two are equal B The latter is greater than the former C The former is greater than the latter D Not necessarily E Depending on the number of samples 31. Randomly select a sample with content n from the same normal population. Theoretically, 95% of the population mean is within the range C A mean plus or minus 1.96 times the standard deviation B mean Add or subtract 2.58 times the standard deviation C Add or subtract 1.96 times the standard error of the mean D Add or subtract 2.58 times the standard error of the mean E None of the above A t value remains unchanged B t value increases C t value decreases D t value is equal to P value E t value increases or decreases A μ1≠μ2 B μ1=μ2 c π1=π2 D π1≠π2 E B=C a> A bar graph B line graph C histogram D circle graph E percentile bar graph EAll research subjects divided according to the population. D All research objects divided according to time. CAll research subjects divided by region. BThe totality of research objects that can be imagined randomly. AA group of homogeneous research subjects determined based on the research purpose. l. The population in statistics refers to: 1. Introduction Statistics test question 2: A bar chart B histogram C line chart D percentile bar chart E scatter chart 50． To describe the distribution of hair mercury levels in 210 healthy adults in a certain place, it is appropriate to draw B 49. To compare the incidence of a certain disease in a certain year in regions A, B, and C, you can use A E. The title is at the top of the table and briefly describes the contents of the table D. Remarks are marked with "*" and written below the table C. The numbers should be right-aligned, the number of decimal places for the same indicator should be the same, and there should be no spaces in the table B. The lines mainly include top lines, bottom lines and horizontal lines under the vertical headings. After analyzing the indicators, there are diagonal lines and vertical lines A. The horizontal headings are the research objects and are listed on the left side of the table; the vertical headings are the analysis indicators and are listed on the right side of the table 48. Regarding the tabulation principle of statistical data, the error is B A bar graph B composition graph C ordinary line Figure D Histogram E Statistical map in a certain place from 1990 to 1997, it is appropriate to draw C 47. To compare the incidence rate of hepatitis Chapter 12 Statistical Tables and Charts E Two pairs of theoretical numbers, and two pairs of C The measured number and the theoretical number D. Two pairs of measured positive absolute numbers and negative absolute numbers A, the numerator and denominator of the two sample rates, B the numerator and denominator of the two constituent ratios 46. The basic numbers of the four grids in the four-grid table are D 45. In the X2 test for comparison of two sample rates, the correct expression of the null hypothesis (H0) should be C D. Eliminate the influence of different internal composition of the data and make the rates comparable. E. Act as a weighted average A to make the large rate smaller, B to make the small rate larger, and C to make the rate better represent the actual level 44. The purpose of calculating the standardized rate is D A composition ratio B relative ratio C absolute number D rate E coefficient of variation 43. To reflect the proportion of the internal components of things, A A composition ratio B relative ratio C absolute number D rate E coefficient of variation 42. The index that reflects the intensity of a certain event should be selected as D C Do not treat the composition ratio as a rate analysis D The comparability between the two E The denominator should not be too small A Hypothesis testing should be done when comparing B Pay attention to the influence of the degree of dispersion 40. If X2≥ =39> 41． When using relative numbers, you should pay attention to the following points. Which one of them is incorrect B A T<5 B T>5 C T<1 D T>5 E should be used 1<T<5 39. For a four-grid table chi-square test, when N>40 and __________, the correction formula E A number of rows × number of columns B n-1 C N-k D (number of rows - 1) (number of columns - 1) E number of rows × columns Number-1 38. The calculation formula for the degrees of freedom in the chi-square test is D D The sample rates are different or not identical. E The sample rate and the overall rate are different. A The population rates are different or not the same B The population rates are different C The sample rates are different 37． Comparing the four sample rates, x2>x20.01(3), it can be considered that A A rate B composition ratio C relative ratio D absolute number E standardized rate 36. There are 1,000 outpatients in a hospital on a certain day, including 400 internal medicine patients. Find 40%. This 40% is B C to facilitate comparison D to express the actual level E to express the relative Level A to conduct significance test B to express the absolute level 35. The purpose of calculating the relative number is C A must be greater than 1 B must be less than l C must be equal to 1 D must be equal to 0 E varies with the data 34 ． The important feature of the composition ratio is the sum of the percentages of each component C Chapter 10 Statistical description and inference of categorical variable data C The variances of the two samples are equal D The population variances of the two samples are equal E The number of cases in the two samples is equal A. The two samples have similar means and equal variances. B. The two samples have similar means. 33. To perform a t test on the difference in means between two samples, the data distribution is required to be approximately normal, and it is also required that D 32. Under the same degree of freedom, P value increases C

2. When a sample is drawn from a population, the reasons for sampling error are:
A. There is variation among individuals in the population. B. Sampling does not follow the randomization principle. 7. The method of drawing lots belongs to: a> 27. For comparison of two large sample rates, you can use: E 28. In the t test comparing the means of two samples, the correct expression of the null hypothesis (H0) should be: B D. None of the above are correct E. A, B are both OK A. u test B, x2 test C, four-square table exact calculation probability method E. x2 test D. U test for comparing two sample means C. t-test for comparing the geometric means of two samples in a group design B. t-test for comparing the means of two samples in a group design A. Paired design t test 26 , 8 cases of hyperlipidemia were treated with a new drug, and the changes in red serum sterol concentration before and after treatment were observed. To know whether the drug is effective, it is appropriate to use: A C. I don’t know whether new drugs or old drugs are better D. It is known that new drugs are not worse than old drugs E. It is known that new and old drugs are almost as good A. It is known that the new drug is better than the old drug B. It is known New drugs are worse than old drugs 25. The premise for one-sided testing is: D E. None of the above are correct C. The difference in the means of the two populations is significant D. The difference in the means of the two samples is significant A. Both groups are average The difference in numbers is not significant B. The difference in the means of the two samples is not significant 24. α=0.05, t>t0.05,ν, statistically it can be considered as (D) A, ≠l.96 B, <1.96 C, =1.96 D, > ;1.96 E, =2.58 23. When the degree of freedom v→∞, the tO.05 value: C E. ±t0.05,υS A. ±1.96S B. ±1.96S C. μ±t0.01,υS D. μ±t0.05,υS 22. Which of the following formulas can be used to estimate the 95% confidence interval of the population mean: A. Standard deviation B. Standard error C. Coefficient of variation D. Range E. Variance 21. The statistical index reflecting the mean sampling error is: 3. Statistical inference of numerical variable data E. The mean is Frequency distribution of the center C. Frequency distribution with the variable as the center D. Frequency distribution with the number of observations as the center A.t value Distribution B. Frequency distribution with the parameter as the center 20. The normal distribution is the frequency centered on: E A. Normal distribution data B. Skewed distribution C. Positive skew distribution D. Negative skew distribution E. Asymmetric distribution 19. Mean and standard deviation are applicable to: A A, 5 B, 5.5 C, 6 D, lO E, 12 C. The sampling error of the sample may be greater D. The representativeness of the sample to the population may be worse A. The greater the variation among observed individuals B. The smaller the variation among observed individuals 18. What does the larger the standard deviation mean? Which of the following is wrong: B A. Arithmetic mean B, geometric mean Number C, median D, range E, rate 17. The most common calculation to express the average level of serological titer data: B A. Full range B. Standard deviation C. Variance D. Coefficient of variation E, range 16. To compare the height variation of 12-year-old boys and 18-year-old men, the indicators that should be used are: D Ask how many hours the average incubation period of food poisoning is: C 15. Food poisoning occurred in a factory, and the incubation periods of 9 patients were: 16, 2, 6, 3, 30, 2, 10, 2, 24+ (hours), C. Both remain unchanged. D. Both All changed E. None of the above are correct A. The mean remains unchanged and the standard deviation changes. B. The mean changes and the standard deviation remains unchanged. A, ：B 13. The distribution properties of a certain numerical variable data are not clear, and the central tendency index needs to be calculated. The following suitable indicators are: C A. Full range B. Standard deviation C. Coefficient of variation D. Interquartile range E. Median 12. The variation indicators are as follows, except: E A. Mean B. Geometric mean C. Median D. Mode E. Range 11. Commonly used averages are as follows, except: E 2. Statistical description of numerical variable data Answer: 1A 2A 3B 4C 5B 6E 7D 8D 9D 10B D. ordered categorical data E. discrete data A , centralized data B. numerical variable data C. unordered categorical data 10. A sample survey of the blood pressure values of 1,000 adults in a certain area. This data belongs to: D. Ordered classified data E. Discrete data A. Centralized data B. Numerical variable data C. Unordered classified data The type of the data is: D Number of patients treated 8 23 6 3 1 Treatment results were cured, significantly improved, worsened and died. 9. A new therapy was used to treat 41 patients with a certain disease. The treatment results are as follows: D. Representative part E. Valuable part A. Any part B. Typical part C. Meaningful part 8. The sample is from the population: A. Stratified sampling B. Systematic sampling C. Cluster sampling D. Simple random sampling E. Two-level sampling D. Research error E. Sample inference population parameters A. Research Sample statistics B. Research population statistics C. Research typical cases 6. The purpose of the sampling survey is: A, 0.01 B, O.05 C, 0.1 D, 0.5 E, 1.O 5. Statistically speaking, it is generally believed that events with P less than or equal to a certain number will not occur in one observation: A. Statistical design B. Data collection C , Organizing data D. Analyzing data E. None of the above are correct 4. The process of making measurement data into frequency tables belongs to which basic step of statistical work: D. The possibility of a certain event happening is very high E. The above None of them are correct A. A certain event will definitely not happen B. A certain event will definitely happen C. The possibility of a certain event happening is very small 3. The probability P=1 means:
C. The selected individuals are not homogeneous D. There are few individuals making up the sample E. The grouping is unreasonable

A. μ1≠μ2 B. μl=μ2 c. 1≠ 2 D. 1= 2 E. π1=π2
29. In the t test, when t>to .o5 v, the conclusion is: C
A, P>O.05 B, P≥O.05 C, P<O.05 D, P≤0.05 E, P≤0.01
30. For two t tests, in addition to the normal distribution of the samples, the following conditions should be met: B
A. The two values are close to B , The two S2 values are close to C, the difference between the two is large
D. The two S2 values are very different, E. None of the above are correct
31. Sample survey of 100 boys and 100 girls each Name, and calculate the mean height and weight respectively. The mean height and weight of the same gender cannot be used for hypothesis testing because: A
A. The data is not comparable B. Height data Not normally distributed
C. The weight data is not normally distributed D. The sample size is small
32. Composed of 10 pairs (20) of data The data is subjected to a paired t test, and the degrees of freedom are equal to: C
A, 10 B, 20 C, 9 D, 18
33. Do a test on the means of the two samples t test, n1=20, n2=20, its degrees of freedom are equal to: C
A, 19 B, 20 C, 38 D, 40 E, 39
4. Statistical description and inference of classified data
34. The purpose of calculating relative numbers is: E
A. To conduct significance testing B. To express the absolute level
C. For the convenience of comparison D. To express the actual level E. To express the relative level
35. There are 1,000 outpatients in a hospital on a certain day, including internal medicine patients. 400 people, find 40%, this 40% is: B
A. Rate B, composition ratio C, relative ratio D, absolute number E, standardized rate
36. When using relative numbers, you should pay attention to the following points. Which one of them is incorrect: B
A. Hypothesis testing should be done when comparing B. Pay attention to the influence of the degree of dispersion a>
C. Do not equate proportion analysis with proportion D. Comparability between the two E. The denominator should not be too small
37. Indicators that reflect the intensity of a certain event Should choose: D
A. Composition ratio B, relative ratio C, absolute number D, rate E, coefficient of variation
38. Reflect the proportion of the internal components of things The size should be selected: A
A. Composition ratio B, relative ratio C, absolute number D, rate E, coefficient of variation
39. The purpose of calculating the standardized rate It is: D
A. Make the big rate smaller, B. Make the small rate bigger C. Make the rate better represent the actual level
D , Eliminate the influence of different internal compositions of the data, making the rates comparable E. Act as a weighted average
40. In the X2 test for comparing two sample rates, the correct expression of the null hypothesis (H0) Should be: C
A, μ1≠μ2 B, μ1=μ2 c, π1=π2 D, π1≠π2 E, B=C
41. Card The calculation formula for degrees of freedom in the square test is: D
A. Number of rows × number of columns B. n-1 C. N-k D. (Number of rows-1) (Number of columns-1) E , number of rows E A, T<5 B, T>5 C, T0.05 44. Comparing the four sample rates, x2>x20.01(3), it can be considered: A A. The population rates are different or not exactly the same. B. The population rates are different. C. , Each sample rate is different D. Each sample rate is different or not exactly the same E. The sample rate and the overall rate are different 45. The important feature of the composition ratio is that the sum of each component is B A. >100% B. =100% C. <100% D. =0 E. Varies with different data 46. From statistics From a scientific point of view, the following indicators are absolute numbers: D A. The number of acute infectious diseases in District A is 1.25 times that of District B B. District A The incidence rate of acute infectious diseases in a certain year is 382/100,000 C. District A accounts for 18% of the acute infectious diseases in a certain city D. A certain district A man is 168 centimeters tall E. The mortality rate of acute infectious diseases in District A in a certain year is 52.2/100,000 5. Statistical tables and charts Overview of medical statistical methods (10 questions) 5. Investigate the publication status of scientific researchers in a certain unit, and count the number of papers published per person per year, which should be classified as A D. Overall statistical indicators E. Variables related to statistical research A. VariablesB. Number of participants in the study C. Statistical indicators of the research sample　　 4. In statistics, the meaning of parameters is　D 　D. Homogeneous individual composition E. Individual composition A. Composition of research objects B. Research variable composition C. Depends on the research purpose 3. The overall should be composed of D A. Research sampleB. Study individual C. Study the correlation between variables D. Overall study E. Collection, arrangement and analysis of research data or information 2. The research content of medical statistics is E D. 120 adult men in the city E. 120 healthy adult men in the city A. All adult men B. All adult men in the city C. All healthy adult men in the city 1． A certain study conducted random sampling and measured the hemoglobin number of 120 healthy adult men in the city. The population of this study is: C "Medical Statistical Methods" test question 3: A. Bar chart B. Histogram C , Line graph D, Percent bar graph E, Statistical map 50. To describe the distribution of hair mercury content in 210 healthy adults in a certain place, it is appropriate to draw: B A. Bar graph B. Line graph C. Histogram D. Circle graph E. Straight bar Composition diagram 49. Comparison The incidence rate of a certain disease in a certain year in regions A, B, and C can be used: A D. Lines require three-line or four-line type E. If there are no numbers, you can leave it blank A. The title is located in the upper center of the table. B. There should be no vertical lines. and slash C. Remarks do not need to be included in the table 48. Which of the following requirements for statistical tables is incorrect: E A. Bar graph B. Composition graph C. Ordinary line graph D. Histogram E , Statistical map 47. To compare the incidence rate of hepatitis in a certain place from 1990 to 1997, it is appropriate to draw: C

A． Count data B. Measurement data C. Overall D. Individual E. Sample
6. For small probability events in statistics, the following statement is correct: B
A. Repeated observations many times will result in an event that will never happen B. In an observation, an event can be expected to not occur C. Events with probability of occurrence less than 0.1 D. An event with a probability of occurrence less than 0.001 E. An event with a probability of occurrence less than 0.1
7. A sample in statistics refers to: D
A. Extract a meaningful part of the population according to the researcher's requirements 9. The number of red blood cells (1012L-1) is: B A, 3.2±t0.05.11 ×0.5 B, 3.2 ±t0.05.12 ×0.5/ a> 5. In the t test formula for paired measurement data comparison, the denominator is C 6. In the paired t test, the pre-medication data minus the post-medication data and the post-medication data minus the pre-medication data, two t tests C C. The t values have opposite signs, but the conclusions are the same A. The t values have opposite signs, but the conclusions are opposite. B. The t values have the same signs, but the conclusions are the same. A. B. C. D. d2S E, A.P <0.05 B.P <0.01 C.P >0.05 D.P =0.05 E, P <0.005 4. The u test for comparing the means of two large samples, |u|=1.98, then the statistical conclusion is D E .It is known that both drug A and drug B are ineffective C. It is known that medicine A is not better than medicine B D. I don’t know whether medicine A and medicine B are both effective A. It is known that both drug A and drug B are effective B. I don’t know whether medicine A or medicine B is better 3. When comparing the efficacy of two drugs, which of the following can be used as a one-sided test ( ). C D. Paired design t test E. X2 test A. Grouped design u test B. Grouped design t test C. Paired design u test 2. 12 women used two instruments to measure vital capacity to measure the maximum expiration rate (l/min). To compare the results of the two methods, you can do: D D. The change in standard error is independent of sample size E. All of the above are true A. The standard error decreases B. The standard error increases C. The standard error does not change 1. In sampling research, S is a fixed value, If the sample content is gradually increased, then the sample: A Statistical inference of numerical variable data (13 questions) Answer: 1.B 2.A 3.D 4.C 5.D 6.D 7.C 8.C 9.C 10 .E 11.B 12.A 13.A E. The larger the standard deviation, the more representative the mean is C. The larger the mean, the smaller the standard deviation D. The larger the mean, the larger the standard deviation　　 A. The smaller the standard deviation, the more representative the mean is. B. The smaller the standard deviation, the less representative the mean is.　 13. The relationship between the mean and the standard deviation is A 　E. 5 one, 7 one, 9 one,… 　C. One 5, one 10, one 15,... D． 0-4, 5-9, 10-1,...　　A. 0 one, 5 one, 10 one,...B． 0-5, 5-10, 10-1,...　 12. When making a frequency table, taking the group interval as 5, which of the following group segments is correctly divided A D. ±1.96 E. ±1.645 A. ±2.58s B. ±1.96s C . ±2.58 11. For the 95% normal value range of normally distributed data, (B　) A. Lognormal B. Left skew C. Right skew D. Skewness E. Normal 10. For the following distribution of data, the mean is equal to the median. E A. 97.5% b. 95% c． 50%D． 5% E. Not sure 9. Under the normal curve. On the horizontal axis, the area from the mean to +∞ is. C A. VarianceB. Standard deviation c. Coefficient of variation D. Full range E. Interquartile range 8. Which of the following can be used to compare the variability of height and weight C A. Arithmetic mean b. Standard deviation c. Median D. Interquartile range E. Variance 7. For skewed distribution data, one of the following items should be used to describe the central tendency of its distribution. C A. Arithmetic mean b. Geometric mean C. Median D. Extremely poor e. 50th percentile 6. Which of the following indicators can be used to describe the degree of dispersion of measurement data. D D.6 and 1.58 E 6 and 2.5 and 6.78 E, 3.2 ±2.58×0.5/ C, 3.2 ±t0.05.11 ×0.5/ D, 3.2±1.96×0.5/ 4. 12 boys from a certain city were randomly selected and their average weight was measured to be 3.2 kg , the standard deviation is 0.5 kg, then the formula of the 95% confidence interval of the overall mean is: C A. The height variation is greater than the weight. B. Height variation is less than weight C. Height variation is equal to weight D. Cannot be compared E. Height variation is not equal to weight 3. The standard deviation of the height of a group of 7-year-old boys is 5cm and the standard deviation of the weight is 3kg. Comparing the degree of variation between the two: D A. Average B. Relative number C. t value D. Standard error E. Probability 2. The main statistical indicators describing measurement data are: A s=1 m =Uncertain E. s=0 mD. =Uncertain =0 mA. =0 s=1 m =1 C. s=0 m =0 B. s 1. The characteristics of the standard normal distribution curve are: B Statistical description of numerical variable data (13 questions) Answer: 1C 2E 3D 4D 5A 6B 7D 8B 9B 10D A. Observation unit B. Numeric variable C. Nominal variable D. Rank variable E. Research individual 10. The therapeutic effect is: D A. Observation unit B. Numeric variable C. Nominal variable D. Grade variable E. Research individual A. Calculate B. Count C. Measure D. Level E. All correct 8. Diastolic blood pressure ≥12.7KPa is considered high blood pressure. Measure 1,000 people. As a result, there are 990 non-hypertensive patients and 10 hypertensive patients. This data belongs to ( )material. B D. Select a representative part of the population according to the random principle E. Overall Each individual in
B. Randomly select any part of the population C. Consciously select a typical part of the population

D and t values have the same signs, but different sizes, and the conclusions are opposite. E, the signs of t values have nothing to do with the conclusion
7. The smaller the item below is, the more reliable it is to use the sample mean to estimate the population mean. C
A. CV B. S C. S D. R E. Interquartile range
8. The assumptions for comparing data on two small sample numerical variables should first be considered. E
A. t-test B. u test C. Rank sum test
D. Both t test and rank sum test can be used E. Does the data conform to the t test or the rank sum test
9. Sampling error refers to D
A. The difference between population parameters and population parameters B. The difference between individual values and sample statistics
C. Differences between overall parameters D. The difference between sample statistics and population statistics　
　E. None of the above is true
10. , the hypothesis (B) is statistically acceptable.
A, B, C, D, E, all of the above are wrong
11. The content of statistical inference: D
A. It is to use sample indicators to estimate the corresponding overall indicators B. It is to test the "hypothesis" in statistics
C. Neither a nor b is D. Both a and b are E. The above are all wrong
12. Comparing the means of two samples, after t test, when the difference is significant, the smaller the P, the explanation: C
A. The greater the difference between the means of the two samples B. The average of the two populations The greater the difference in numbers
C. The more reason to believe that the two population means are different D. The more reason to believe that the two sample means are different
E. The sample mean is different from The population means are different
13. The statistical index indicating the size of the sampling error of the mean is C
A. Standard deviation B. Variance C. Standard error of the mean D .Coefficient of variation E. Range

Answer: 1.A 2.D 3.C 4.D 5.C 6.C 7.C 8.E 9.D 10.B 11. D 12.C 13.C

Statistical description and inference of categorical variable data (13 questions)
1. The main statistical indicators for describing categorical variable data are: B
A. Mean B. Relative number C. Variation coefficient D. Correlation coefficient E. Percentile
2. Male population/female population, This indicator is: C
A. Rate B. Composition ratio C. Relative ratio D. Dynamic sequence E. Not a relative number
3. There is a composition ratio The important features are ( ). A
A. The sum of percentages must be equal to 100% B. The sum of percentages must be less than 100%
C. The sum of percentages must be greater than 100% D. None of the above are true E. All the above are wrong
4. Standardized overall mortality rate ( ). A
A. Only as a basis for comparison, it reflects a relative level
B. It reflects the actual level C. It does not change with the selection of standards Change
D. It reflects the intensity of what actually happens E. None of the above
5. Regarding relative numbers, which of the following statements is wrong? D
A. Relative numbers are the ratio of two related indicators
B. Commonly used relative numbers include relative Ratio, rate and composition ratio
C. When calculating relative numbers, the denominator must be large enough
D. Although rate and composition ratio have different meanings, they are similar in nature and often Can be mixed
E. When calculating relative numbers, the denominator is not required to be large enough
6. Randomly select 200 men and 100 women for a survey on a certain parasitic disease. For the subject, the infection positivity rates were measured to be 20% and 15% respectively, then the combined positivity rate _____C_____
A.35% B.16.7% C.18.3% D. Unable to calculate E. 30%
7. The purpose of standardizing the rate when comparing tuberculosis mortality rates in two places is: D
A. In order to better reflect the population Actual death level
B. Eliminate the impact of the different total number of people in the two places
C. Eliminate the impact of the different mortality rates of each age group
D. Eliminate the impact of the different age composition of the population in the two places
E. None of the above is correct
8. There is no need for correction in the chi-square test of four-grid table data, and the condition that should be met is (D).
A. The total number of cases is greater than 40 B. The theoretical number is greater than 5 C. The actual numbers are all greater than l
D. The total number of cases is greater than 40 and the theoretical numbers are greater than Or equal to 5 E. The total number of cases is less than 40
9. The purpose of calculating relative numbers is C
A. To conduct significance testing B. In order to express the absolute level
C. For ease of comparison D. In order to express the actual level E. In order to express the relative level
10. When using relative numbers, you should pay attention to the following points. Which one of them is incorrect? B
A. Hypothesis testing should be done when comparing B. Degree of dispersion and degree of variation C. Don’t treat composition ratio as rate analysis D. Comparability between the two E. The denominator should not be too small
11. Comparing the four sample rates, χ2>χ20.01(3), it can be considered: A
A. Each population rate is different Or not all the same B. Each population rate is different C. Each sample rate is different D. Each sample rate is different or not all the same E. Each population rate and each sample rate are different or not all the same
12. The test is suitable for comparison: D
A. The significance of the difference between two rates B. The significance of the difference between multiple rates C. The significance of the difference between two or more composition ratios D , all of the above are OK E, all of the above are wrong
13. A researcher inoculated 50 sputum samples on A and B culture media to observe the growth of Mycobacterium tuberculosis and wanted to compare the two. Whether the culture effect of the culture medium is consistent, please see the table below for the information. Question: The statistical method that should be selected is: C
A. Exact probability method B. Test of four-grid table data C. Test of paired count data
D. Row Test of multiplied tabular data E. t test of paired measurement data
Total of culture medium A and culture medium B

﹢ ﹣
﹢ 23 12 35
﹣ 7 8 15
Total 30 20 50

Answer: 1.B 2.C 3.A 4 .A 5.D 6.C 7.D 8.C 9.C 10.B 11.A 12.D 13.C

Statistical tables and charts (4 questions) A. Bar graph B. Circle graph C. Line graph D. Histogram E. Semi-logarithmic line graph 2. A hospital collected recent outpatients For information on the composition of disease types, it is advisable to draw: B A. Ordinary line graph B. Histogram C. Bar graph D. Scatter graph E. Statistical map
1. In order to show the changes in infant mortality rate in a certain place in the past 20 years, it is appropriate to draw (A).

3. The picture shows the age distribution of Japanese encephalitis patients in a certain place and a certain year. It should be drawn: D
A. Bar chart B. Percent bar chart C. Circle Figure D. Histogram E. Line graph
4. Compare the case fatality rates of three infectious diseases, diphtheria, Japanese encephalitis, and dysentery, in a certain place in 1995. The chosen statistical graph is C< a i=3> A. Histogram B. Semi-logarithmic graph C. Bar graph D. Line graph E. Percent graph Answer: 1.A 2.B 3.D 4.C Exercise 4 of Medical Statistical Methods: Overview of Medical Statistical Methods 1. The sample is from the population: D< a i=8> A. Any part B. Typical part C. Meaningful part D. Representative part E. Valuable part 2. Parameters refer to: C A. Mutual control B, standard control C, experimental control D, self-control E, blank control 7. t A. The mean of the two populations, the difference is not significant Sex B, two population means, the difference is significant A. The data should be comparable B. Don’t make conclusions absolute C. Choose an appropriate test method based on the data D. The denominator should not be too small E. Data It should obey the normal distribution 6. Which of the following Notes on items that are not t-tests: D E. The more reason to believe that the two population means are different C. It means that the mean of the two samples is different. The greater the difference from the population mean D, the more reason to believe that the two sample means are different A. It means that the difference between the means of the two samples is greater. B. It means that the difference between the means of the two populations is greater. 5. In the t test comparing the means of two samples, the result is P<0.05, which is statistically significant. The smaller P is: E D. The larger the sample size, the smaller the standard error E. The standard error is often used to estimate the confidence interval of the total mean B. The standard error is small, indicating that using the sample mean to represent the population mean is more reliable C. The standard deviation is large, and the standard error is also large A. The standard error is large, indicating that using the sample mean to represent the population mean is more reliable 4. The following ( ) is wrong: B a. It is to use sample indicators to estimate the corresponding overall indicators. b. It is to test the "hypothesis" in statistics. c. Neither a nor b is d. Both a and b are E. All the above are wrong. 3. The content of statistical inference. D 2 B Cm1＝mA 2 D E.μd=0m¹1m 2. Two samples of completely random design For mean comparison, the null hypothesis can be: A A standard deviation B variance C standard error of mean D coefficient of variation E, full range 1. Sampling error indicating the mean The statistical index of size is: C Statistical inference of numerical variable data C. Possible sampling error of the sample The larger the D, the less representative the sample may be of the population. E. None of the above are correct A. The greater the variation among observed individuals B. The smaller the variation among observed individuals 10. The meaning of the larger standard deviation is as follows: The wrong understanding is: A 8. Which of the following formulas can be used to estimate the medical normal range (95%): A A. X±1.96S B. X±1.96SX C. μ±1.96SX D. μ±t0.05,υSX E. A test paper has 3 questions, each question is 1 point. 20% of the class gets 3 points, 60% gets 2 points, 10% gets 1 point, and 10% gets 0 points. The average score is C? A.95% B.45% C.97.5% D.47.5% E.49.5% 7. On the horizontal axis, the area under the standard normal curve from 0 to 1.96 is: D A. Mean B. Geometric mean C. Median D. Quartile E. Relative number 6. To calculate the average level of a certain serum hemagglutination inhibitory antibody titer, it is appropriate to use: B A. Range B. Standard deviation C. Variance D. Coefficient of variation E. Standard error 5. Compare the degree of variation in height and weight. Suitable indicators: D A. Range B. Standard deviation C. Mean D. Coefficient of variation E, standard error 4. Description 1 When analyzing the discrete trend of symmetric (or normal) distribution data, the most suitable index to choose is B A.9 B.7 C.10.5 D.11 E, 12 3. A set of variable values, the sizes of which are 10, 12, and 9 respectively , 7, 11, 39, where the median is: C A. Full range B, standard deviation C, coefficient of variation D, interquartile range E, median 2. The variation indicators are as follows, except: E A. Find full distance B. Fixed group distance C. Group segments D. Mark E. Make distribution map 1. The steps for preparing a frequency table are as follows, except: E Statistical description of numerical variable data A. Necessary event B. Impossible event C. Random event D. Small Probability event E, accidental event 10. In statistics, events with P≤0.05 or P≤0.01 are often called D 9. The control group does not receive any treatment, belonging to E C to facilitate experiments D to reduce and offset the interference of non-experimental factors E None of the above is correct A to facilitate statistical processing B to strictly control the influence of random errors 8. The experimental design requires strict compliance with four basic principles. It is for: D E Collect data, organize data, analyze data, and make inferences C design, collect data, organize data, analyze data D collect data, organize data , check and analyze data A collect data, design, organize data, analyze data B collect data, organize data, design, statistical inference 7. The correct step in statistical work is C A Stratified sampling B Systematic sampling C Cluster sampling D Simple random sampling E Two-stage sampling 6. The method of drawing lots belongs to D A. Observation unit B, numerical variable C, nominal variable D, grade variable E, research individual 5. The therapeutic effect is: D A. Observation unit B. Numeric variable C. Nominal variable D. Grade variable E. Research individual 4. Pulse number ( times/minute) is: B A. Research sample statistics B. Research population statistics C. Research typical cases D. Research error E. Sample inferred population parameters 3. The purpose of sampling is: E A. Number of participating individuals B. Number of research individuals C. Overall statistical indicators D. Sum of samples E. Statistical indicators of samples

B. The mean of the two samples, the difference is not significant D. The mean of the two samples, the difference is significant E. None of the above
8. To evaluate a certain city Whether the height of an 8-year-old boy is too tall or too short, the statistical method that should be used is: A
A. Use the 95% or 99% normal value range for the height of an 8-year-old boy in the city to evaluate
B. Conduct a hypothesis test on height differences to evaluate C. Use the 95% or 99% confidence interval of the height mean to evaluate
D. Cannot make an evaluation E None of the above are correct
9. Among the two samples from the same population, which of the following indicators has a smaller value and its sample mean is more reliable in estimating the population mean? A A.Sx B.S C.x D.CV E S2
10. The reason for the mean sampling error is A
A. Individual differences b. Group differences C. The sample means are different D. The population mean is different. None of the above are correct
11. Under the same degree of freedom, the P value increases C
A t value remains unchanged B t value increases C t The value decreases D The t value is equal to the P value E The t value increases or decreases
12. After determining the test level of the hypothesis test, the same data B
A . If the one-sided t test is significant, the two-sided t test must be significant
B. If the two-sided t test is significant, the one-sided t test must be significant
C. If the two-sided t test is not significant, then the one-sided t test is also not significant
D. The results of the single and double t tests are not related. E None of the above is correct
13. When comparing the means of two samples, the following test levels are used to make the smallest type II error A
A, α=0.05 B, α=0.01 C, α=0.10 D. α=0.02 E, α=0.15
Statistical description and inference of categorical variable data
1. When using relative numbers, the following points should be noted, except: E< a i=19> A. The denominator should not be too small. B. Do not treat the composition ratio as a ratio analysis. C. Comparability. D. Hypothesis testing should be done when comparing. E. Average level And the degree of variation 100/100 rC, Number of actual patients/number of people on the register 100/100 E, None of the above are correct D, Number of people tested/number of people tested 2. To reflect the changes in the incidence of hepatitis A in a certain city for five consecutive years, C A. Composition diagram B． Bar chart C. Histogram D. Line graph E. Graph 4. To compare the annual average concentration of SO2 in seven districts of a city, a ( ) graph should be drawn: B A. Bar graph B. Histogram C. Line graph D. Percent bar graph E. Statistical map 3. Describe a certain place The distribution of hair mercury levels in 210 healthy adults in the area should be drawn: B A. Bar graph B. Histogram C. Ordinary line graph D. Percent bar graph E. Circle composition graph D. The title is at the top of the table. Briefly describe the contents of the table E. Remarks are marked with "*" and written below the table C. The numbers are right-aligned, the number of decimal places for the same indicator is the same, and there should be no spaces in the table B. The lines mainly include the top line, the bottom line and the horizontal lines below the vertical headings. It is not appropriate to have Slashes and vertical lines A. The horizontal heading is the research object , listed on the right side of the table; the vertical headings are analytical indicators, listed on the left side of the table 1. Regarding the listing principle of statistical tables, which one is wrong? A Statistical tables and charts D The two population rates are the same E The sample rate and the population rate are different A The two sample rates are different B The two sample rates are the same C The two population rates are different 13. In the four-square table chi-square test, X2<X20.05 (v) can be considered D D. The sample rates are different or not all the same. E. The sample rates and the overall rates are different A can only be used for the adjusted chi-square test B cannot be used for the chi-square test C does not need to be adjusted for the chi-square test 12. For comparison of percentages, there are 1 A theoretical number is less than 5 and greater than 1, and the others are all greater than 5. C A. Percentage B. Thousandths rate C. Ten thousandths rate D. Hundred thousandths rate E Doesn’t matter 11. Birth rate habits Used above: B D. Eliminate the influence of different internal composition of the data, making the rates comparable E. Act as a weighted average A. Make the large rate smaller, B. Make the small rate larger, C. Make the rate more efficient. Better represent the actual level 10. The purpose of calculating the standardized rate is: D A. Each population The rates are different or not all the same. B. The population rates are all different. C. The sample rates are all different. 9. Comparing the four sample rates, x2>x20.01(3), it can be considered: A D. The incidence of the disease will be reduced E. The survival rate of this disease increases A. The prevalence of the disease will increase B. The prevalence of the disease will decrease C. The incidence of the disease will increase 8. If a new treatment method can prolong life but cannot cure the disease, the following will happen: A A. Time point prevalence B. Composition ratio C. Incidence rate D. central tendency e. Comparative comparison 7. The number of hepatitis patients in a certain place in a certain year accounts for 10.1% of the number of infectious diseases in the same year. What kind of indicator is this: B A. 0 b． 1C． 2 D． 4 E.5 6. The degree of freedom of the four-cell table X2 test is ____. B C. Two pairs of measured positive absolute numbers and negative absolute numbers D. Two pairs of measured numbers and theoretical numbers E. None of the above is correct A. The numerator and denominator of the two sample rates B. The numerator and denominator of the two constituent ratios 5. The basic numbers of the four cells in the X2 four-cell table are: C E. None of the above A. Reflect the seriousness of what happened B. The proportion of the internal composition of things C. The ratio of two related indicators D. Dynamic changes 4. The constituent indicators in relative numbers are explained: B A. Case fatality rate B. Cause of death composition ratio C. Order of cause of death D. Mortality rate E. None of the above is correct 3. The main indicators explaining the death level in a region are: D A. 100/100 r100/100 B. The number of detected patients/the number of registered patients r Actual number of patients/number of people tested 2. The detection rate of a certain occupational disease: D

General practitioner training statistics test questions
l. The population mentioned in statistics refers to: A
A. The same population determined according to the purpose of the research All qualitative research objects.
B. All imaginary research objects.
C. All research objects divided by region.
D. All research objects divided according to time.
E. All research subjects divided according to the population.
2. Comparing the hepatitis incidence rate in a certain place from 1990 to 1997 should be drawn: C
A. Bar graph B. Composition graph C. Ordinary line graph D. Histogram E. Statistical map
3. The process of making measurement data into a frequency table is a statistical work Which basic step: C
A. Statistical design B. Collect data C. Organize data D. Analyze data E. None of the above is correct
4. From a population When selecting samples, the reasons for sampling errors are: A
A. Variation among individuals in the population B. Sampling does not follow the randomization principle
C. Sampling The individuals are not homogeneous D. There are few individuals making up the sample E. The grouping is unreasonable
5. The probability P=0 means: A
A. A certain event It will definitely not happen B. A certain event will definitely happen C. The possibility of a certain event happening is very small
D. The possibility of a certain event happening is very high E. None of the above are correct
6. A sample survey of the blood pressure values of 1,000 adults in a certain area was made into a frequency table. This data belongs to: A
A. Measurement data B. Count data C. Grade data D. Semi- Quantitative data E, discrete data
7. The distribution nature of certain measurement data is not clear. To calculate the central tendency index, the following __C______ is suitable
A, X B, G C, M D, S E, CV
8. The important feature of the composition ratio is the sum of the percentages of each component_C_______
A. It must be greater than 1 B. It must Less than l C, must be equal to 1 D, must be equal to 0 E, varies with data
9. After adding (or subtracting) the same number to each observation value: B
A. The mean remains unchanged, but the standard deviation changes. B. The mean changes, and the standard deviation remains unchanged.
C. Both remain unchanged. D. Both change. E. None of the above are correct
10. Food poisoning occurred in a factory, and the incubation periods of 9 patients were: 16, 2, 6, 3, 30, 2, 10, 2, 24+ (hours), A, 5 B, 5.5 C, 6 D, 10 E, 12 11. To compare the height variation of 12-year-old boys and 18-year-old men, the appropriate indicators are: D A. Full range B. Standard deviation C. Variance D. Coefficient of variation E. Extremely Poor 12. Which of the following requirements for statistical tables is incorrect: E A. The title should be located in the upper center of the table. B. There should be no vertical lines and Slash C. Remarks do not need to be included in the table D. Lines must be three-line or four-line E. No need to fill in if there are no numbers 13. Statistics It is generally believed that the event P<____B______ will not occur in one observation A. 0.01 B. O. 05 C, 0.1 D, 0.5 E, 1. O 14. The most common calculation to express the average level of serological titer data: B A. Arithmetic mean B, geometric mean C, median D , full range E, rate 15. Which of the following formulas can be used to estimate the medical normal value range (95%): A A. X±1.96S B. ±1.96SX C, μ±1.96SX D, μ±t0.05,υSX E, X±2.58S 16. Comparison of the means of two samples In the t test, the result is P<0.05, which is statistically significant. The smaller P is: E A. It means that the difference between the means of the two samples is greater. B. It means that the difference between the means of the two populations is greater. C. It means that the mean of the two samples is different. The greater the difference from the population mean D, the more reason to believe that the two sample means are different E. The more reason to believe that the two population means are different 17. Standard deviation The greater the meaning, the following understanding is wrong: B A. The greater the variation among observed individuals B. The smaller the variation among observed individuals C , the greater the sampling error of the sample may be D. the representativeness of the sample to the population may be worse E. None of the above are correct 18. The purpose of calculating relative numbers is ：C A. In order to conduct significance test B. In order to express the absolute level C. For ease of comparison D. In order to express the actual level E. In order to express the relative level 19. The mean and standard deviation are applicable to: C A. Positively skewed distribution B. Negatively skewed distribution C. Normal distribution D. Skewed distribution E. Asymmetric distribution 20. The sample is the population: C A. Valuable part B. Meaningful part C. Representative part D. Any part of E. Typical part 21. There are 1,000 outpatients in a hospital on a certain day, including 400 internal medicine patients. Find 40%. This 40% is: B A , rate B, composition ratio C, relative ratio D, absolute number E, standardized rate 22. For comparison of four sample rates, x2>x20.01(3), it can be considered: A A. Each population rate is different or not identical. B. Each population rate is different. C. Each sample rate is different. D. Each sample rate is different or not identical. E. Sample rate and population rate are all different 23. A paired t test is performed on data consisting of 10 pairs (20 items) of data. The degrees of freedom are equal to: C A, 10 B, 20 C, 9 D, 18 E, 19 24. Perform a t test on the means of the two samples, n1=20, n2=20, and the degrees of freedom are equal to: C A, 19 B, 20 C, 38 D, 39 E, 40 25. Which of the following is not a note of the t test: D A . The data should be comparable. B. Avoid making conclusions absolute. C. Choose the appropriate test method based on the data. D. The denominator should not be too small. E. The data should obey the normal distribution. 26. In one In a sampling study, when the sample size gradually increases: B A. The standard deviation gradually decreases B. The standard error gradually decreases C. The standard deviation gradually increases D. The standard error gradually increases E. Both the standard deviation and the standard error gradually increase 27. To compare the incidence of a certain disease in a certain year in regions A, B, and C, you can use: A A. Bar graph B. Line graph C. Histogram D. Circle graph E. Bar graph

28. To describe the distribution of hair mercury content in 210 healthy adults in a certain place, it is appropriate to draw: B
A. Bar graph B. Histogram C. Line graph D. Hundreds Strip chart E, statistical map
29. The calculation formula for degrees of freedom in the chi-square test is: D
A. Number of rows × number of columns B. n- 1 C. N-k D. (Number of rows - 1) (Number of columns - 1) E. Number of rows , and _____E_____, the correction formula should be used. A, T<5 B, T>5 C, T0.05 32. Under the normal distribution curve, the horizontal axis goes from the mean μ to μ+l. The area of 96σ is D A. 97.5% B. 95% c. 48.8% D. 47.5% E. 45% 33. When a doctor collects statistics on department case data, he intends to use the arithmetic mean to express the average level. What kind of data should be used: C A ． Variable values with small individual differences B. Variable values with large individual differences C. Variable values with the same nature D. Variable values with different properties E. Variable values with the same difference 34. The coefficient of variation expresses the data: D A. Variation number B. Symmetrical distribution C. Central tendency D. Relative variation E. Average level 35. When determining the normal range of a certain indicator for normal people, the object of investigation is: B A. People who have never been sick B. Exclude people with diseases and factors that affect research indicators C. People who have only suffered from mild diseases that did not affect the indicators being studied D. Excluding people who have suffered from a certain disease or been exposed to a certain factor E. None of the above 36. The following are statements about the reference value range, among which the correct one is E A. The reference value range should be established based on 95% of the normal human range B. If a certain indicator of a person is randomly measured and its value is within 95% of the normal range, then the person's indicator should be considered normal C. If an indicator exceeds the reference value range, it should be abnormal D. Find the reference value range of normal data. The higher the accuracy, the better E. The so-called normal and healthy are relative, and there is some degree of pathological state in normal or healthy people 37. The relationship between the mean and the standard deviation is: E 46. t A. mean of two populations, The difference is not significant B. The difference between the two population means is significant C. The two sample means are not significantly different D. The two sample means are significantly different E. All of the above No 47. To reflect the proportion of the internal components of a thing, you should choose: A A. Composition ratio B. Relative ratio C. Absolute number D. Ratio E. Coefficient of variation 48. The purpose of calculating the standardized rate is: D A. Make the large rate smaller, B. Make the small rate larger C. Make the rate better represent the actual level D. Eliminate the influence of different internal composition of the data and make the rate comparable E. Play the role of weighted average 49 , in the t test of two sample means, the test hypothesis (H0) is: B A, μ1≠μ2 B, μ1=μ2 C, X1≠X2 D, X1=X2 E, X1 =X2 50. In the X2 test for comparison of two sample rates, the correct expression of the null hypothesis (H0) should be: C A, μ1≠μ2 B , μ1=μ2 c, π1=π2 D, π1≠π2 E, B=C Reference answer: 1. A 2, C 3, C 4 , A 5, A 6, A 7, C 8, C 9, B 10, C 11, D 12, E 13, B 14, B 15, A 16, E 17, B 18. C 19, C 20, C 21. B 22, A 23, C 24, C 25, D 26, B 27, A 28, B 29, D 30, E A. Composition ratio B. Relative ratio C. Absolute ratio Number D, rate E, coefficient of variation 45. The indicators reflecting the intensity of an event should be selected as: D E. Frequency distribution with the mean as the center C. Variable-centered frequency distribution D. Frequency distribution centered on the number of observed cases A. Frequency distribution with the t value as the center B. Frequency distribution with centered parameters 44. The normal distribution is: E C. Different indicators have large differences in means D. The same indicators have large differences in standard deviations E. None of the above A. The same indicator, the mean difference is large B. For different indicators, the mean difference is small 43. Using the coefficient of variation to compare the degree of variation is suitable for: c C. Do not treat composition ratio as rate analysis D. Comparability between the two E. The denominator should not be too small A. Hypothesis testing should be done when comparing B. Pay attention to the influence of discreteness 42. When using relative numbers, you should pay attention to the following points. Which one of them is incorrect: B D. Overall statistical indicators E. Variables related to statistical research A. variable b. Number of participants in the study C. Statistical indicators of the research sample 41. In statistics, the meaning of parameters is: D E. The difference between individual values and sample statistics C. The difference between sample statistics and population parameters D. Differences between overall parameters A. The difference between individual values and sample statistics B. Differences between sample statistics 40. The definition of sampling error is: C A. rate b. relative comparison c. Composition ratio D. Frequency e. Frequency 39. Explain that the ratio of two related similar indicators is B E. The title is at the top of the table and briefly describes the contents of the table D. Remarks are marked with "*" and written below the table C. The numbers should be right-aligned, the number of decimal places for the same indicator should be the same, and there should be no spaces in the table B. The lines mainly include top lines, bottom lines and horizontal lines under the vertical headings. After analyzing the indicators, there are diagonal lines and vertical lines A. The horizontal headings are the research objects and are listed on the right side of the table; the vertical headings are the analysis indicators and are listed on the left side of the table 38. 18. Regarding the tabulation principle of statistical data, the error is B E. The smaller the standard deviation, the more representative the mean is C. The larger the mean, the smaller the standard deviation D. The larger the mean, the larger the standard deviation A. The larger the standard deviation, the more representative the mean is. B. The smaller the standard deviation, the less representative the mean

31、A 32、D 33、C 34、D 35、C 36、E 37、E 38、A 39、B 40、C
41、D 42、B 43、D 44、E 45、D 46、A 47、A 48、D 49、B 50、C

Statistics question bank
l. The population mentioned in statistics refers to:
A. Homogeneous research objects determined according to the research purpose All.
B. All research subjects based on random imagination
C. All research subjects divided by region
D. Based on All research subjects divided by time
E. All research subjects divided according to population
2. In statistical work, the primary task of organizing data is a> 11. After adding the same number to each observation value 22. Comparing the four sample rates, x2>x20.01(3), it can be considered: C. The sample rates are different. D. The sample rates are different or not all the same. E. Percent bar graph A , Bar graph B, Ordinary line graph C, Histogram D, Circle graph 27. To compare the incidence of a certain disease in a certain year in regions A, B, and C, you can use: D. The standard error gradually increases E. Both the standard deviation and the standard error gradually increaseA. The standard deviation gradually decreases B. The standard error gradually decreases C. The standard deviation gradually increases 26. In a sampling study, when the sample size gradually increases: E. The data should obey the normal distribution A. The data should be comparable B. Don’t make conclusions absolute 25. Which of the following is not a note of the t test? Matters: A, 19 B, 20 C, 38 D, 39 E, 40 24. Conduct a t test on the means of the two samples, n1=20, n2= 20, its degrees of freedom are equal to: A, 10 B, 20 C, 9 D, 18 E, 19 23. A paired t test is performed on data composed of 10 pairs (20 items) of data. The degree of freedom is equal to: E. The sample rate and the population rate are different A. The population rates are different or not all the same. B. The population rates are all different. A. Rate B. Composition ratio C, relative ratio D, absolute number E, standardized rate 21. There are 1,000 outpatients in a hospital on a certain day, including 400 internal medicine patients. Find 40%. This 40% is D. Any part of E. Typical part A. Valuable part B. Meaningful part C. Representative part 20. The sample is randomly selected from the population: D. Data with unknown frequency distribution type E. Asymmetrically distributed data A. Positively skewed distribution data B. Negatively skewed distribution data C. Normally distributed data A. X±1.96S B. X±1.96SX C. μ±1.96SX E. In order to express the relative level C. To facilitate comparison D. In order to express the actual level A. In order to conduct hypothesis testing B. In order to express the absolute level 18. The purpose of calculating relative numbers is: D. μ±t0.05,υSX E, X±2.58S 13. To compare the height variation of 12-year-old boys and 18-year-old men, the indicators that should be used are: A. Arithmetic mean B, geometric mean C, median D, range E, rate 16 , representing the average level of serological titer data is most commonly calculated: D. Groups of 15 to 20 E. Divide into any group A. Groups of 5 to 10 B. Groups of 8 to 15 C. Groups of 10 to 15 15. When preparing a frequency table for measurement data, the general number of groups is E. Leave it blank if there are no numbers C. Remarks do not need to be included in the table D. Lines must be in three-line format or Four-line type A. The title is located in the upper center of the table B. Vertical lines and slashes should not be included in the table 14. Which of the following requirements for statistical tables is incorrect: A. Range B, standard deviation C, variance D, coefficient of variation E, range , 5 B, 5.5 C, 6 D, lO E, 12 The average incubation period of food poisoning is ____ ____ (hours) 12. Food poisoning occurred in a factory, and the incubation periods of 9 patients were: 16, 2, 6, 3, 30, 2, 10, 2, >24 (hours), E. The mean becomes larger, but the standard deviation remains unchanged C. Both remain unchanged. D. Both change. A. The mean remains unchanged, and the standard deviation changes. B. The mean changes, and the standard deviation remains unchanged. E. Varies with data A , B. Must be less than l C. Must be equal to 1 D. Must be equal to 0 9. Data with unknown frequency distribution type should be calculated to express its average level A. Measurement data B. Count data C. Hierarchical data D. Semi-quantitative data E. Discrete data 8. A sample survey of the blood pressure values of 1,000 adults in a certain area was made into a frequency table. This data belongs to: A. 0.01 B. O. 05 C, 0.1 D, 0.5 E, 1. O 7. The statistically low-probability event usually refers to P< __________ event, E. The grouping is unreasonable C. Sampling. The individuals are not homogeneous D. There are fewer individuals making up the sample 6. Samples are randomly selected from a population. The reasons for sampling errors are: A. Variation among individuals in the population. B. Sampling does not follow the randomization principle. A. Statistical design B. Collecting data C. Organizing data D. Analyzing data E. None of the above are correct 5. Prepare measurement data The process of forming a frequency table belongs to which basic step of statistical work: A. Bar graph B. Composition graph C. Ordinary line graph D. Histogram E. Statistical map in a certain place from 1990 to 1997 It is advisable to draw: 4. Compare the incidence of hepatitis D. A certain event The possibility of the event happening is very high E. None of the above are correct A. A certain event will definitely not happen B. A certain event will definitely happen C. The possibility of a certain event happening is very small 3. Probability P=0, it means E. None of the above
A. Design grouping B. Table to be organized C. Check data D. Grouping

28. To describe the distribution of hair mercury content in 210 healthy adults in a certain place in a certain year, it is appropriate to draw:
A. Bar graph B. Histogram C. Ordinary line graph D. Percent bar chart
E. Statistical map
29. The calculation formula for degrees of freedom in the chi-square test is:
A. Number of rows × number of columns B. n-1 C. N-k
D. (Number of rows-1) (Number of columns-1) E. Number of rows×Number of columns-1< a i=6> 30. Perform a four-cell chi-square test. When N>40 and ____ ___, the correction formula should be used. A, T<5 B, T>5 C, T0.05 32. Under the normal distribution curve, from the mean μ to μ+l on the horizontal axis. The area of 96σ is A. 97.5% B. 95% c. 48.8% D. 47.5% E. 45% 33. The size of the standard deviation indicates A. The degree of dispersion between individual observation values B. The average level of individual observation values < a i=15> C. The sampling error of the sample mean D. The degree of dispersion of the sample mean E. None of the above 34. The coefficient of variation represents the data of: A. Normal distribution B. Symmetric distribution C. Central tendency D. Relative variation E. Average level 35. The 95% confidence interval of the overall mean of large sample data can be expressed as follows: A. B. C. D． E. 36. Indicates the average height of a 12-year-old boy. The most commonly calculated is A. Arithmetic mean b. Median C. Geometric mean D. Coefficient of variation E. Standard deviation 37. The relationship between the mean and the standard deviation is: A. The larger the standard deviation, the more representative the mean is. B. The standard deviation The smaller the mean, the less representative the mean C. The larger the mean, the smaller the standard deviation D. The larger the mean, the larger the standard deviation E , the smaller the standard deviation, the more representative the mean is 38. The sampling error is due to A. Calculation causes B. Caused by sampling C. Measurement caused D. Caused by instrument not being calibrated E. Caused by unskilled operation 39. Explain the ratio of two relevant indicators as A. Rate B. Relative ratio C. Composition ratio D. Frequency E. Frequency 43. Using the coefficient of variation to compare the degree of variation is suitable for: 41, C 42, B 43, C 44, A 45, D 46, B 47, A 48, D 49, B 50, C 31, A 32, D 33, A 34, D 35, C 36, A 37, E 38, B 39, B 40, C 21, B 22, A 23, C 24, C 25, B 26, B 27, A 28, B 29, D 30, E 11, E 12, C 13, D 14, E 15, B 16, B 17, A 18, C 19, C 20, C 1 , A 2, C 3, A 4, C 5, C 6, A 7, B 8, A 9, C 10, C Reference answer: A. μ1≠μ2 B. μ1=μ2 C. X1 ≠X2 D, X1=X2 E, =65> A. μ1≠μ2 B. μ1=μ2 c. π1=π2 D. π1≠π2 E. B=C 49. For the t test comparing the means of two samples, the null hypothesis (H0) is 46. t A. The means of the two populations are different B. The means of the two populations are the same C. The means of the two samples are different D. The means of the two samples are the same E. None of the above 47. The proportion that reflects the internal components of things should be selected A , composition ratio B, relative ratio C, absolute number D, rate E, coefficient of variation 48. The most commonly used method to describe the average level of a set of skewed distribution data is A. Composition ratio B, relative ratio C, absolute number D, rate E, coefficient of variation 45. Reflect a certain event The indicators of occurrence intensity should be selected: D. Data with unknown distribution type E. None of the above A. Normal distribution data B. Skewed distribution data C. Lognormal distribution data 44. The arithmetic mean is suitable for E. None of the above C. The units are different, but the mean difference is large. D. The units are the same. The standard deviation is small A. The units are the same, but the mean difference is large. B. The units are different, and the mean difference is small. E. The denominator should not be too small C. Do not compare the composition ratio Ratio analysis D. Comparability between the two A. Hypothesis testing should be done when making comparisons. B. Pay attention to the influence of discreteness. 42. Pay attention to the following when using relative numbers Point, which one of them is incorrect: A. Rate B. Composition ratio C. Relative ratio D. Variance E. Median 41. Ratio of medical staff in a hospital , should be calculated E. None of the above C. Difference between sample indicators and overall indicators D. Difference between overall indicators A. The difference between individual values and sample indicators B. The difference between individual values 40. The definition of sampling error is:

Question 51: Which of the following descriptions about the linear regression equation Y=a+bX is incorrect.

　　A. The two coefficients that determine the regression line are a and b

　　B.a>0 means that the intersection point of the straight line and the vertical axis is above the origin

　　C.b>0 means that the straight line goes from the lower left to the upper right

　　D.b=0 means the straight line passes through the origin

　　E. The regression line must pass through the point (——X, Y)

　　Question 52: The null hypothesis of the paired t test (two-sided test) can generally be expressed as.

　　A. μ1=μ2

　　B. μ1≠μ2

　　C. μd=0

　　D. μd≠0

　　E. There is no difference in the means of the two samples

　　Question 53: The degrees of freedom of the χ2 test of the R×C contingency table are ( )

　　A.R-1

　　B.C-1

　　C.R+C-1

　　D.R×C-1

　　E.(R-1)(C-1)

Question 54: Infer the difference between the two population rates from the difference in the two sample rates. If P<0.05, then.

　　A. There is a big difference between the two sample rates

　　B. There is a big difference in the rates between the two groups

　　C. The difference between the two sample rates and the two population rates is statistically significant

　　D. The difference between the two population rates is statistically significant

　　E. The difference between one of the sample rates and the overall rate is statistically significant

　　Question 55: Pay attention when making statistical tables.

　　A. The title is written below the table

　　B. The horizontal heading is on the upper row of the table, and the vertical heading is on the left side of the table.

　　C. The horizontal heading is on the left side of the table, and the vertical heading is on the upper row of the table.

　　D. There can only be a top line and a bottom line in the table

　　E. There are no numbers in the table that can be represented by...

　　Question 56: Which of the following is not the main content of health statistics research.

　　A. Basic principles and methods of health statistics

　　B. Health statistics, disease statistics, growth and development statistics

　　C. Health service statistics

　　D. Medical demographics

　　E. Community medical care

　　Question 57: In hypothesis testing, the relationship between P value and α is.

　　A. The larger the P value, the larger the α value.

　　B. The larger the P value, the smaller the α value.

　　C. Both the P value and α value can be set in advance by the researcher

　　D. Neither the P value nor the α value can be set in advance by the researcher.

　　E. The size of the P value has nothing to do with the size of the α value

　　Question 58: Comparing the three sample rates, we get χ2>χ20.01(2), which can be.

　　A. The three overall rates are different or not all the same

　　B. The three overall rates are not the same

　　C. The three sample rates are all different

　　D. The three sample rates are different or not all the same

　　E. Two of the three overall rates are different

　　Question 59: The composition ratio is used to reflect.

　　A. The intensity with which a certain phenomenon occurs

　　B. Represents the ratio of two similar indicators

　　C. Reflect the proportion of each part of something to the whole

　　D. Indicates the arrangement of a certain phenomenon in time sequence

　　E. Both A and C above are correct

　　Question 60: The normal range of a certain physiological indicator (such as systolic blood pressure) or biochemical indicator (such as blood sugar level) of a certain group of people (such as adult men) generally refers to.

　　A. The fluctuation range of this indicator among all people

　　B. The fluctuation range of this indicator among all normal people

　　C. The fluctuation range of this indicator among most normal people

　　D. The fluctuation range of this indicator among a small number of normal people

　　E. The fluctuation range of this indicator at different times for a person

Health statistics test questions and answers (1)

1. Use the survey data on myopia among students aged 6 to 16 in a certain place to create a statistical graph to reflect the age distribution of patients. The types of graphs available are ______.

　　A. Ordinary line drawing

　　B. Semi-logarithmic line chart

　　C. Histogram

　　D. Bar chart

　　E. Compound bar chart

　　【Answer】C

　　2. In order to reflect the age distribution of nasopharyngeal cancer death cases in a certain area during a five-year period, ______ can be used.

　　A. Histogram

　　B. Ordinary line chart

　　C. Semi-logarithmic line chart

　　D. Bar chart

　　E. Compound bar chart

　　【Answer】E

　　3. In order to reflect the changes in the age-specific mortality rate of male lung cancer in a certain area from 2000 to 1974, ______ can be used.

　　A. Histogram

　　B. Ordinary line chart

　　C. Semi-logarithmic line chart

　　D. Bar chart

　　E. Compound bar chart

　　【Answer】E

　　4. To investigate the preventive effect of a certain vaccine in children, all 1,000 susceptible children in a certain place were vaccinated. After a certain period of time, 300 children were randomly selected from them for effect measurement, and 228 positive results were obtained. If you want to study the effectiveness of the vaccine among children in this area, ______.

　　A. The sample of this study is 1,000 susceptible children

　　B. The study sample was 228 positive children

　　C. The study population is 300 susceptible children

　　D. The study population is 1,000 susceptible children

　　E. The population of the study was 228 positive children

　　【Answer】D

　　5. If you want to make statistical inferences from a sample, the sample should be __________.

　　A. A typical part of the population

　　B. Any part of the whole

　　C. A randomly selected part of the population

　　D. A meaningful part selected from the whole

　　E. A part of the population with clear information

　　【Answer】C

　　6. The following correct statement about the mean is______.

　　A. When the sample size increases, the mean also increases

　　B. The mean is always greater than the median

　　C. The mean is always greater than the standard deviation

　　D. The mean is the average of all observations

　　E. The mean is the average of the maximum and minimum values

　　【Answer】D

　　7. After susceptible children in a certain place were injected with hepatitis B vaccine, 100 children were randomly selected to measure their hepatitis B surface antibody titer levels. To describe their average levels, ______ should be used.

　　A. Mean

　　B. Geometric mean

　　C. Median number

　　D. Variance

　　E. Interquartile range

　　【Answer】B

　　8. Based on the incubation period data of 164 patients with a certain type of salmonella food poisoning, someone used the percentile method to calculate the one-sided 95% upper limit of the incubation period as 57.8 hours, which means: ______.

　　A. Approximately 95 people have an incubation period of less than 57.8 hours

　　B. About 5 people have an incubation period greater than 57.8 hours

　　C. About 5 people have an incubation period of less than 57.8 hours

　　D. About 8 people have an incubation period greater than 57.8 hours

　　E. About 8 people have an incubation period of less than 57.8 hours

　　【Answer】D

　　9. The incorrect statement below is ______.

　　A. The variance divided by its degrees of freedom is the mean square

　　B. Analysis of variance requires that each sample comes from an independent normal population.

　　C. Variance analysis requires that the variances of the populations in which each sample is located are equal.

　　D. In the analysis of variance with a completely randomized design, the mean square within the group is the mean square of the error.

　　E. For analysis of variance in a completely randomized design, F=MS between groups/MS within groups

　　【Answer】A

　　10. After subtracting the same constant from each variable value in the two sets of data, perform a hypothesis test to compare the means of the two samples______.

　　A.t value remains unchanged

　　B.t value becomes smaller

　　C.t value becomes larger

　　D.t value becomes smaller or larger

　　E.Cannot judge

　　【Answer】A

　　11. When the mortality rate of a certain disease in places A and B is standardized, the standard selection is ______.

　　A. Cannot use data from A.

　　B. Cannot use data from location B

　　C. The combined data of place A and place B cannot be used

　　D. Data from place A or place B can be used

　　E. None of the above is correct

　　【Answer】D

　　12. The following are numerical variables______.

　　A. Gender

　　B. Patient’s white blood cell count

　　C. Blood type

　　D. Curative effect

　　E. Number of people infected with a certain disease

　　【Answer】B

　　13. The following statement about samples is incorrect ______.

　　A. The sample is randomly selected from the population

　　B. The population from which the sample comes should be homogeneous

　　C. There should be enough individuals in the sample

　　D. There must be no variation in the population from which the sample comes.

　　E. The sample content can be estimated

　　【Answer】D

　　14. The following are categorical variables___________.

　　A.IQ score

　　B.Heart rate

　　C. Number of days in hospital

　　D. Gender

　　E. Bust

　　【Answer】D

　　15. In sampling research, when the number of samples gradually increases_____.

　　A. The standard error gradually increases

　　B. The standard deviation gradually increases

　　C. The standard deviation gradually decreases

　　D. The standard error gradually decreases

　　E. The standard deviation approaches 0

　　【Answer】D

　　16. A hospital admitted 202 patients with lumbar disc herniation in one year. The frequency distribution of their ages is as follows. In order to express the data vividly, _____ is suitable.

　　Age (years): 10～20～30～40～50～60～

　　Number of people: 6 40 50 85 20 1

　　A. Line diagram

　　B. Bar chart

　　C. Histogram

　　D. Circle diagram

　　E. Scatter plot

　　【Answer】C

　　17. Regarding the composition ratio, the incorrect one is _____.

　　A. The increase or decrease in the proportion of a certain part in the composition ratio will correspondingly affect the proportion of other parts.

　　B. The composition ratio indicates the intensity of a certain phenomenon.

　　C. The composition ratio explains the distribution of each component within a certain thing.

　　D. If the internal composition is different, the rate can be standardized

　　E. The sum of the composition ratios must be 100%

　　【Answer】B

　　18. If the quantitative relationship between vital capacity and body weight is analyzed and the body weight value is to be used to predict vital capacity, then _____ is used.

　　A. Linear correlation analysis

　　B. Rank correlation analysis

　　C. Linear regression analysis

　　D. Analysis of variance

　　E. Case-control study

　　【Answer】C

　　19. According to the following information, the sample indicators indicate _____.

　　　　　　　　　　Therapy A Therapy B

　　　　　　Number of patients with the condition, number of cures, cure rate (%) Number of patients, number of cures, cure rate (%)

　　Light 40 36 90 60 54 90

　　Heavy duty 60 42 70 40 28 70

　　Total 100 78 78 100 82 82

　　A. Therapy B is better than therapy A

　　B. Treatment A is better than treatment B

　　C. Treatment A and Treatment B are equally effective

　　D. In this information, therapies A and B cannot be compared.

　　E. None of the above is correct

　　【Answer】C

20. If F drug = 7.604, P<0.01; F block = 1.596, P>0.05. According to α = 0.05 level, the tumor inhibitory effects of the four drugs and the tumor weight of the five random blocks can be inferred respectively. for_____.

　　A. Tumor weight is different between drug groups and also different between blocks.

　　B. It cannot be considered that the tumor weight is different between the drug groups, and it cannot be considered that the tumor weight is different between the blocks.

　　C. Tumor weight is different between drug groups, but it cannot be considered to be different between groups.

　　D. It cannot be considered that the tumor weight is different between drug groups, but it is different between blocks.

　　E. The drugs are quite different and cannot be considered to be different between the groups.

　　【Answer】C

Health statistics test questions and answers (2)

1. Linear correlation and linear regression analysis were performed on two quantitative variables at the same time. If r is statistically significant (P<0.05), then _____.

　　A.b No statistical significance

　　B.b is highly statistically significant

　　C.b has statistical significance

　　D. It is not certain whether b is statistically significant

　　E.a is statistically significant

　　【Answer】C

　　2. Regarding non-parametric tests based on ranks, which of the following statements is incorrect _____.

　　A. In the signed rank sum test, the difference value is zero and does not participate in ranking.

　　B. The normal approximation method in the rank sum test method for comparing two samples is a parametric test

　　C. When the normality assumption is met, the probability of making a Type II error is greater for non-parametric tests than for parametric tests.

　　D. When the sample is large enough, the rank sum distribution is approximately normal.

　　E. The rank sum test is suitable for testing differences in hierarchical data, sortable data and unknown distribution data.

　　【Answer】B

　　3. The probability of a random event is______.

　　A.P=1

　　B.P=0

　　C.P=－0.5

　　D.0≤P≤1

E.－0.5<P<0.5

　　【Answer】D

　　4. When the means of two samples are compared and the t test is used to conclude that the difference is statistically significant, the smaller the P, it means ______.

　　A. The greater the difference between the two sample means

　　B. The greater the difference between the two population means

　　C. The more reason there is to believe that the means of the two populations are different

　　D. The more reason there is to believe that the means of the two samples are different

　　E. The more reason there is to believe that the means of the two populations are the same

　　【Answer】C

　　5. In order to study the effect of hypoxia on the heart rate of normal people, 50 volunteers participated in the experiment, and their heart rates were measured before and after the experiment.

　　What statistical test method should be used to better analyze this data_____.

　　A. Paired t test

　　B. Grouped t-test

　　C. Grouped rank sum test

　　D. Paired rank sum test

　　E. Test for homogeneity of variances between two groups

　　【Answer】A

　　6. When doing signed rank sum test, record the statistic T as the smaller rank sum, then the correct one is _____.

　　A. The larger the T value, the smaller the P value.

　　The larger the B.T value, the more reason to reject H0

　　C.P value has nothing to do with T value

　　D. The smaller the T value, the smaller the P value.

　　E. None of the above is correct

　　【Answer】D

　　7. Analysis of variance requires ______.

　　A. The means of each sample are equal

　　B. The variances of each population are equal

　　C. The population means are equal

　　D. The variances of the two samples are equal

　　E. Two samples come from the same population

　　【Answer】B

　　8. Compare the white blood cell count levels of patients with atypical pneumonia and common pneumonia. If so, a unilateral test can be performed.

　　A. It is known that the white blood cell counts of both groups of patients were reduced.

　　B. It is known that the white blood cell counts of both groups of patients are elevated.

　　C. It is not clear which group has changes in white blood cell count levels

　　D. It is known that the white blood cell count of patients with atypical pneumonia is not higher than that of ordinary pneumonia

　　E. The overall variance of the white blood cell count values in the two groups is not equal.

　　【Answer】D

　　9. Calculate the incidence rate of pneumonia in children in a certain place. The incidence rates of pneumonia in boys and girls are 21.2% and 19.1% respectively. It can be considered as ______.

　　A. The incidence of pneumonia is higher in boys than in girls

　　B. Standardization should be carried out before comparison.

　　C. The data are not comparable and cannot be directly compared.

　　D. Hypothesis testing should be conducted before drawing conclusions.

　　E. None of the above is correct

　　【Answer】D

　　10. When comparing two rates, there is no need to standardize the rates in the following cases: ______.

　　A. Different internal composition

　　B. The internal composition is the same

　　C. The number of people of each age is unknown

　　D. Lack of number of deaths by age

　　E. It is difficult to find the standard population composition

　　【Answer】B

　　11. Under what circumstances does the χ2 test of data in a four-grid table do not require correction______.

　　A.T>1 and n>40

　　B.T>5 or n>40

　　C.T>5 and n>40

D.1<T<5

E.T>5且n<40

　　【Answer】C

　　12. If you want to compare the efficacy of three drugs (ineffective, improved, markedly effective, recovered), which one is better, it is best to choose ______.

　　A.t test

　　B. Analysis of variance

　　C.χ2 test

　　D. Rank sum test

　　E.u 检验

　　【Answer】D

　　13. The incorrect statement below is _____.

　　A. Without individual differences, there would be no sampling error.

　　B. The size of sampling error is generally expressed as standard error.

　　C. Good sampling design method can avoid the occurrence of sampling error

　　D. Medical statistics mainly come from statistical reports, medical work records, special surveys or experiments, etc.

　　E. Sampling error is the difference between sample statistics and population parameters and the difference between sample statistics caused by sampling

　　【Answer】C

　　14.The fundamental difference between experimental design and survey design is _____.

　　A. The experimental design is based on animals.

　　B. Survey design targets people

　　C. The survey design can be randomly divided into groups

　　D. Experimental design can artificially set processing factors

　　E. None of the above is correct

　　【Answer】D

　　15. Among the following sampling survey methods, under the premise of the same sample size, the one with the smallest sampling error is _____.

　　A. Simple random sampling

　　B. Systematic sampling

　　C. Stratified sampling

　　D. Cluster sampling

　　E. Multi-stage cluster sampling

　　【Answer】C

　　16. Perform linear correlation analysis on the two variables, r=0.46, P>0.05, indicating ______ between the two variables.

　　A. Relevant

　　B. No relationship

　　C. No linear correlation

　　D. No causal relationship

　　E. There is an accompanying relationship

　　【Answer】C

　　17. A doctor studied the role of Salvia miltiorrhiza in preventing coronary heart disease. The experimental group used Salvia miltiorrhiza, and the control group received no treatment. This kind of control belongs to ______.

　　A. Experimental control

　　B. Blank control

　　C. Mutual comparison

　　D. Standard control

　　E. Historical comparison

　　【Answer】B

　　18. In the rank sum test comparing two independent samples, the observation values of the experimental group are 0, 0, 7, 14, 32, 40, and the observation values of the control group are 0, 1, 2, 4, 4, 8. Editor Ranks with zero values in the ranks should be coded as ______ respectively.

　　A.2，3；1

　　B.1.5，1.5；3

　　C.2，2；2

　　D.2.5，2.5；1

　　E. Not participating in the ranking

　　【Answer】C

　　19. Rank sum test for comparison of two samples (the number of samples in the two groups is equal), if the hypothesis is true, then for the sample: ______.

　　A. The rank sum of the two groups is equal

　　B. The absolute values of the rank sums of the two groups are equal.

　　C. There is a big difference between the rank sums of the two groups.

　　D. The difference between the rank sums of the two groups is generally not very large.

　　E. The differences between the rank sums of the two groups are equal. Medical statistics simulation test questions (A)

1. Multiple-choice questions: Choose the best answer among A, B, C, D and E, and fill in the letter of the answer in the corresponding underlined space.

(1 point each question)

1. The basic steps in health statistics include _____.

A Animal experiments, clinical trials, comprehensive surveys and sampling surveys

B Data collection, statistical description, parameter estimation and statistical inference

C Experimental design, data collection, data sorting and statistical analysis

D Data collection, data checking, data sorting and data analysis

E Statistical design, statistical description, statistical estimation and statistical inference

2. The following _____ are not quantitative data.

A. Body mass index (weight/height 2) B. Albumin to globulin ratio

C. Cell mutation rate (%) D. Percentage of neutrophil cells (%)

E. Number of smokers among middle school students

3. Regarding the production of frequency tables, the following _____ statement is correct.

A. The more groups the frequency table has, the better B. The lower limit of the frequency table should be greater than the minimum value

C. The upper limit of the frequency table should be less than the maximum value. D. Generally, frequency tables use equally spaced groupings.

E. The range of the frequency table is the sum of the minimum and maximum values

4. To compare the variation of the same data between the two groups of height and sitting height, _____ should be used.

A. Coefficient of variation (CV) B. Standard deviation (s) C. Variance (s2)D. Extremely poor (R) E. interquartile range

5. The area under the left and right normal curves outside the range from μ to μ+1.96s is _____.

Ａ．2.5% B．95% C．5.0% D．99% E．52.5%

6. In the following statement about hypothesis testing, the incorrect statement is _____.

A. When it is known that the blood pressure-lowering effect of drug A is only better than or equal to that of drug B, a one-sided test can be selected

B. The smaller the test level is, the smaller the probability of making a Type I error.

C. The smaller the test power 1-? is set, the smaller the probability of making a Type II error.

D. The smaller the P value, the more reason to reject H0

E. When other conditions are equal, the test efficiency of two-sided test is lower than that of one-sided test

7. After subtracting the same constant from each variable value in the two sets of data, do a t-test on the difference between the two sample means ( ), ____.

A. The t value remains unchanged. B. The t value becomes smaller. C. The t value becomes larger.

D. The t value becomes smaller or larger E. Unable to judge

8. Randomly divide 90 hypertensive patients into three groups and treat them with methods A, B and C respectively. The difference in blood pressure before and after taking the medicine is the therapeutic effect. If you want to compare whether the effects of the three methods are the same, the correct answer is ____.

A. Perform a t test to compare the differences between three samples. B. Perform a variance analysis to compare the differences between three samples.

C. t-test analysis of variance for paired design data before and after taking medication

D. Perform variance analysis on compatibility group design data E. None of the above is correct

9. A doctor treated two patients with retinitis, and one case was effective. Which of the following statements is incorrect: _____.

A. The effective rate is 50%. B. It is best expressed as an absolute number

C. When it must be expressed as a rate, its credible interval should also be given

D． The denominator is too small and relative numbers are unreliable E. Unable to know overall effectiveness

10. According to the survey, the crude mortality rate of coronary heart disease in both places A and B is 4/105. After unifying the age composition, the landmark rate of A is 4.5/105 and that of place B is 3.8/105. Therefore it can be considered as _____.

A. The average age of the people in place A is older than that in place B. B. The actual mortality rate of coronary heart disease among people in place A is higher than that in place B

C. The composition of the elderly in place A is larger than that in place B D. The mortality rate from coronary heart disease in all age groups in place A is higher than that in place B

E． The average risk of death from coronary heart disease in people in place A is higher than that in place B

11. An example that is not suitable to be described by the Poisson distribution is _____.

A. Distribution of the number of traffic accidents that occurred on the Guangzhou-Shenzhen Expressway in a certain period of time B. Distribution of the number of E. coli per milliliter of water sample

C. Distribution of the number of particles emitted by radioactive materials per unit time D. Distribution of the number of certain insects in unit space

E. Distribution of the number of hepatitis B patients in a certain population

12． Surveying 1,600 residents in a certain place, the roundworm infection rate is 50%, then the 95% confidence interval of the overall rate is

_____。

A．47.55～52.45％ B．48.75～51.25％ C．45～55％

D． 49.68～50.32% E． No inferences can be made from this information

13. The following is not what the χ2 test is for.

A. Infer whether there is a difference between two or more population rates

B. Is there any correlation between the two attributes of the cross-classified data?

C. Test the goodness of fit between the frequency distribution and the theoretical distribution

D. Infer whether there is any difference between two or more overall composition ratios

E. Infer whether there is a difference between two or more population means

14. In the rank sum test comparing two groups of samples, the observed values of the experimental group are 0,3,7,14,32, and the observed values of the control group are,0,2,4,4,8. Ranks with zero values in the ranking should be coded as ______ respectively.

A. 1; 2,3 B. 3; 1.5,1.5 C. 2; 2,2 D. 1; 2.5,2.5 E. Not participating in ranking

15. According to the survey data on myopia among students aged 6 to 16 in a certain place, the age distribution of patients can be reflected by _____.

A. Ordinary line graph B. Semi-logarithmic line graph C. Histogram D. Bar graph E. Compound bar graph

16. The correlation coefficient r between the two variables X and Y is calculated based on the sample. After t test, P<0.01, which can be considered _____.

A. There is a close correlation between X and Y B. B. The overall correlation coefficient ρ=1 C. The overall correlation coefficient ρ=0

D. Overall correlation coefficient ρ≠0 E. Overall correlation coefficient ρ>0

17. For clinical trials of different doses of a drug with a long half-life, the following _____ design is not suitable.

A. Paired design B. Completely randomized design C. Crossover design

D. Compatibility group design E. None of the above designs are suitable

18. The life expectancy of the current life table is _____.

A. Affected by the number of people B. Comparisons between different regions cannot be made

C. Affected by the age-specific composition of the population D. It is a comprehensive reflection of the mortality rate of each age-specific

E. is the average age at death

19. Compared with the experiment, _______________.

A. The non-research factors are more strictly controlled in the survey. B. The survey does not involve human intervention in the research subjects.

C. The survey results are more reliable D. The survey design should follow the principles of randomness and balance

E. Survey studies can have smaller samples

20. In the clinical follow-up study of a certain chemotherapy drug for the treatment of lung cancer, the data that are not censored are _____.

A. The follow-up subject died of other diseases B. The follow-up subject immigrated abroad during the follow-up period

C. The follow-up subject failed to complete treatment due to serious side effects. D. The follow-up subject was not dead by the end of the study.

E. The follow-up subject loses contact

2. Fill-in-the-blank questions: Fill in the blanks in the sentences with appropriate nouns or phrases. (2 points per question)

1. In research, the researcher measures and observes a certain characteristic of each observation unit. This characteristic is called _____

. The measured value of _____ is called _____.

2. When establishing the test hypothesis, it should be noted that the test hypothesis is for __________, not for __________.

3. When making statistical charts, the title describes the content of the data and is located in the _____ of the chart. If necessary, indicate ______ and _______.

4. The conditions that should be met when determining the sample content are: (1) Establish a test hypothesis, (2) Determine __________, (3) Put forward the expected

__________, (4) You must know some information about the population that can be inferred from the sample, such as __________ and ____________.

5. Range is the difference between __________ and __________ in all data. It describes the magnitude of data variation.

3. Explanation of nouns: Briefly explain the following nouns. (4 points each)

1. Type II error 2. Non-parametric test 3. Normal value range 4. Intra-group variation

4. Short answer questions: Briefly answer the following questions. (6 points each)

1. Briefly describe how to describe the central tendency and dispersion trend of a set of measurement data

2. Describe the significance and relationship between Type I error and Type II error in hypothesis testing.

3. Try to compare the basic idea of variance analysis of completely randomized design and randomized block design data.

4. The hospital plans to study the efficacy of a new drug in treating hypertension. Try to determine the three elements in the research design.

5. Describe the relationship between death probability, survival probability and survival rate.

5. Discussion and calculation questions (12 points each)

1. A study investigated the fluoride content in drinking water and the prevalence of skeletal fluorosis among residents in mountainous, hilly, plain and coastal areas. The following table asks: 1)

Is there any relationship between the fluoride content in drinking water and the prevalence of skeletal fluorosis? 2) Some people say that if the correlation coefficient test result is P<0.05, it can be considered that the high fluoride content in drinking water is one of the reasons for the high incidence of skeletal fluorosis, right?

Fluorine content (mg/l) X 0.48 0.64 4.00 1.48 1.60 2.86 3.21 4.71

Prevalence rate (%) Y Y 22.37 23.31 25.32 22.29 28.59 35.00 46.07 46.08

2. In a local health service survey, 400 households were randomly sampled. Their average annual medical expenditure was 947 yuan, and the standard deviation was 291 yuan. Assuming that family medical expenses are approximately normally distributed, please estimate the 95% annual medical expense expenditure range of these families, and estimate the average annual medical expense expenditure of local families.

Medical statistics simulation test questions (B)

1. Multiple-choice questions: Choose the best answer among A, B, C, D, and E, and fill in the letter of the answer in the underline (1 point for each question)

1. In medical statistics, the relationship between the sample and the population is __________.

A sample is a representative part of the population B sample is the most distinctive part of the population

C The sample is a typical part of the population D The sample is a meaningful part of the population

E A sample is a carefully selected portion of the population

2. Of the following definitions of probability, __________ is wrong.

A. When the probability is less than 0.05, it is an impossible event B. When the probability is equal to 1, it is an inevitable event

C. When the probability is between 0 and 1, it is a random event

D. When the number of repeated experiments is large enough, the frequency of event occurrence approaches the probability

E. When the probability is equal to zero, it is a non-random event

3. Frequency tables cannot __________.

A. Reflect the characteristics of frequency distribution B. Facilitate further statistical analysis and calculation C. Facilitate the discovery of outliers

D. Accurately estimate the value of the arithmetic mean E. Used to classify data

4. When describing central tendencies in quantitative data, the following statement is incorrect about __________.

A. The mean is suitable for symmetrically distributed data B. Both the geometric mean and the median are suitable for positively biased distributions

C. For the same positively biased distribution data, the estimated mean value is less than the median value

D. The mean value of symmetrically distributed data is equal to the median value

E. The geometric mean is particularly suitable for describing bacteriological and immunological detection indicators.

5. When using a large number of independent samples from the same population to estimate a population parameter, the correct statement about the 95% confidence interval (CI) is __________.

A. The 95%CI of approximately 95% of the samples covers the overall parameter

B. For each 95%CI, the overall parameter is about 95% likely to fall within it

C. The 95%CI of each sample is the same

D. For each 95% CI, there is a 95% probability of covering the overall parameter E. None of the above statements are correct

6. In hypothesis testing, regarding the P value and the ? value, which of the following statements is incorrect is __________.

A. The α value is a negligible, small probability value determined in advance by the decision-maker

B. The P value is the probability of the current value and more extreme situations occurring under the condition that H0 is established.

C. The α value does not have to be 0.05, it can even be 0.15 according to actual needs

D. In the same hypothesis test, the P value obtained when doing a one-sided test is smaller than the P value obtained when doing a two-sided test.

E. The smaller the α value, the more reliable the conclusion is.

7. When the number of groups is equal to 2, for the same data, the relationship between analysis of variance and t test is ____.

A. Completely equivalent and F=t B. The results of variance analysis are more accurate C. t-test results are more accurate

D. Completely equivalent and t= E. None of the above is correct

8. Which of the following statements about analysis of variance is correct is ____.

A. Analysis of variance is used to compare whether the overall variance of each group is equal.

B. The results of analysis of variance are statistically significant, indicating that the means of each sample come from the same population.

C. When judging the P value corresponding to the F value in analysis of variance, you need to check the two-sided boundary value table

D. The larger the F value obtained by analysis of variance, the greater the difference in the population means.

E. The smaller the F value obtained by analysis of variance, the less reason to doubt that H0 is established.

9. To investigate the preventive effect of a certain vaccine in children, all 1,000 susceptible children in a certain place were vaccinated. After a certain period of time, 300 children were randomly selected from them for effectiveness measurement, and 228 positive results were obtained. To study the effectiveness of the vaccine among children in this area, _________.

A. The sample for this study was 1000 susceptible children B. The sample for this study was 228 positive children

C. The population of the study is 300 susceptible children D. The population of the study is 1000 susceptible children

E. The study population was 228 positive children

10. The unique characteristic of the Poisson distribution is ______.

A. Discrete distribution B. The parameter is the population mean C. The variance is equal to the mean

D. When the sample is small, it is a biased distribution. E. When the sample is large enough, it is approximately normal.

11. When comparing two rates, the purpose of standardization is to ______.

A. Reduce the difference between the two rates B. Make the two rates more representative of the actual levels of the two populations

C. To make the two rates more representative of the relative levels of the two populations. D. To compare any two rates, they must be standardized first.

E. Instead of hypothesis testing, find the difference between two rates

12. Use method A and method B to detect 100 confirmed cancer patients respectively. The positive rate of method A is pA, and the positive rate of method B is pB. The method to test the difference in positivity rate between two methods should be ______.

A. The u test that tests whether the two sample rates are equal B. The u test that tests whether the two population rates are equal

C. χ2 test to test whether the two sample rates are equal D. χ2 test to test whether the two population rates are equal

E. χ2 test to determine whether the population rates of two non-independent samples are equal

13． The result of the rank sum test comparing two independent samples is determined to be ______.

A.The bigger T is, the bigger P is. B. The larger T, the smaller P. C. The T value is within the boundary range, and P is smaller than the corresponding?

D． The T value is within the boundary range, and P is greater than the corresponding? E. None of the above is correct

14. Regarding rank-based nonparametric tests, which of the following statements is incorrect ______.

A. In the signed rank test, the difference value is zero and does not participate in ranking.

B. In the rank sum test of randomized block design data, each group is mixed and ranked

C. When the normality assumption is met, the probability of making a Type II error is greater for non-parametric tests than for parametric tests.

D. When the sample is large enough, the rank sum distribution is approximately normal.

E. The rank sum test is suitable for testing differences in hierarchical data, sortable data and data with unknown distribution.

15. To compare the prevalence of several diseases in a certain place in two years, ______ can be used.

A. Histogram B. Compound bar graph C. Line graph D. Composition ratio bar graph D. Circle graph

16. Regression analysis is the study of ______.

A. The correlation between the changes of the two variables X and Y. B. The direction of the changes of the two variables X and Y.

C. The quantitative relationship that the dependent variable depends on the change of the independent variable D. The closeness of the change of the two variables

E. The relative proportion of one variable to another variable

17. In order to reduce the impact of the measurement sequence on the treatment results of comparing new drugs and conventional drugs, which of the following measures should be best used in statistical design______.

A. Set up a control group B. Randomization arrangement C. Increase the number of experiments D. Blind method E. None of the above

18. Regarding the life table, the following correct statement is ______.

A. The current life table data comes from a survey of a specific population at a certain point in time.

B. Group life table data comes from a survey of a specific group of people at a certain point in time.

C. Life expectancy, also known as average life expectancy, refers to the average age of all survey subjects at the time of death.

D. The data obtained by following up the death situation of a specific population can be used for current life table analysis.

E. Because life expectancy is affected by the age composition of the population, life expectancy in different regions cannot be directly compared.

19. Regarding random sampling, the correct statement below is ______.

A. Simple random sampling is suitable for large-scale sample surveys

B. When students’ student numbers are arranged according to their admission scores, systematic sampling can be used in the sample survey to evaluate students’ scores.

C. The advantage of cluster sampling is that the sampling error is smaller

D. Stratified sampling can control the impact of non-research factors on survey results through stratification

E. Only one sampling method can be used in a sample survey

20. In the following indicators, the denominator of ______ is not the average population.

A.Cause-specific mortality rate B.Crude mortality rate C.Incidence rate of a certain disease D.Infant mortality rate E.None of the above

2. Fill-in-the-blank questions: Fill in the blanks in the sentences with appropriate nouns or phrases. (2 points per question)

1. Design is a ____________ link in the entire research and is also the basis for future work.

2. Since the life table is calculated based on age group mortality, the indicators in the life table are not affected by population ______

Due to the influence of ______, the life table indicators of different groups of people are well comparable.

3. When the researcher does not know the population parameters, a certain number of observation units are randomly selected from the population as ______ for ________. The process of using sample indicators to illustrate population characteristics is called ______.

4. In the analysis of variance of completely random design data, the total variation can be decomposed into two parts, ________ and ________, and the corresponding total degrees of freedom can also be decomposed into ________ and ________.

5. In correlation regression analysis, if r and b are calculated simultaneously for the same set of data, their _________ are consistent and _________ are equivalent.

3. Explanation of nouns: Briefly explain the following nouns. (4 points each)

1. Test power 2. Parametric test 3. Confidence interval 4. Variation between groups

4. Short answer questions: Briefly answer the following questions. (6 points each)

1. Try to compare the relationship and significance of standard deviation and standard error.

2. Please briefly describe the statistical methods and applicable conditions that can be used for independent sample hypothesis testing of two population means.

3. Briefly describe the application conditions, advantages and disadvantages of non-parametric testing.

4. Briefly describe the relationship between binomial distribution, Poisson distribution and normal distribution.

5. Describe the differences and connections between linear correlation and linear regression.

5. Discussion and calculation questions (12 points each)

1. A doctor wants to compare the efficacy of three antitussive drugs and analyze the time that the three antitussive drugs delay cough. The results are in the table below after analysis of variance. 2. Please supplement and complete the analysis of variance. 3. Explain the results.

Table ANOVA table of delayed cough time of three antitussives

Source of variation SS ?ν MS F P

Variation between groups 4994.167

intragroup variation

Total variation 31810.000 39

2. The measured urinary 17-ketosteroid excretion in senile chronic bronchitis patients and healthy people is shown in the table below. Compare the mean difference between the two groups to see if there is any statistical significance and interpret the results.

Table 17-ketosteroid excretion in urine (mg/24h) in elderly patients with chronic bronchitis and healthy people

Patient group 2.90 5.41 5.48 4.60 4.03 5.10 5.92 4.97 4.24 4.36 2.72 2.37 2.09 7.10

Healthy group 5.18 8.49 3.14 6.46 3.72 6.64 4.01 5.60 4.57 7.71 4.99

　　【Answer】D

　　20. In the simple linear regression analysis, the regression coefficient was -0.30, which was statistically significant after testing, indicating ______.

　　A. The influence of X on Y accounts for 30% of the variation of Y

　　B.X increases by one unit, Y decreases by 30% on average

　　C.X increases by one unit, Y decreases by 0.30 units on average

　　D.Y increases by one unit, X decreases by 30% on average

　　E.Y increases by one unit, and X decreases by 0.30 units on average.

　　【Answer】C

China Medical University Online Education College

Medical Statistics Review Questions

1. Best choice question

1. What is qualitative data among the following data?

A Weight (kg) B Blood type (A, B, O, AB) C Hemoglobin (g/L)

D Sitting height index (%, sitting height/height) E White blood cell count (units/L)

2. The following information is classified as _______

A White blood cell count (cells/L) B Blood type (A, B, O, AB) C Weight (kg)

D Patient's condition grade (mild, moderate, severe) E Sitting height index (%, sitting height/height)

3． Random samples in medical scientific research refer to _______

A A part of the population B The entire research object C A special part of the population

D A representative part of the population E A particularly representative sample of a part of the research object

4. The basic steps of statistical work are_______

A Design, collect data, organize data and analyze data

B Design, statistical analysis, statistical description and statistical inference

C Select objects, calculate statistical indicators, parameter estimation and hypothesis testing

D Collect data, calculate mean, standard deviation and standard error

E Collect data, organize data and analyze data

5. The small probability event in statistics refers to the probability of a random event _______

A is equal to 0.05 B is less than or equal to 0.05 C is greater than 0.05 D is less than 0.05 E is greater than or equal to 0.05

6. The main research object of medical statistics is _____.

A. Random events b. inevitable event c. Impossible event D. An event that is highly unlikely to occur E. An event that is highly likely to occur

7. Compile a frequency table with a group number of 10. When determining the group distance______

A. The maximum value is usually rounded to 1/10 as the group distance. B. The minimum value is usually rounded to 1/10 as the group distance.

C. Often 1/10 of the range is rounded up as the group distance. D. The group distance is equal to the range.

E. Often half of the range is rounded up as the group distance

8. Two important characteristics of frequency distribution are______

A Central tendency and distribution type B Central tendency and dispersion trend C Standard deviation and mean deviation

D Symmetric distribution and skew distribution E Types of data

9. For some infectious diseases that mainly affect children, the age distribution of patients is concentrated on the younger side, which is called ______

A normal distribution B positively skewed distribution C negatively skewed distribution D uniform distribution E symmetrical distribution

10. When you want to express the average level of data for which there is no definite data at the end, the index that should be used is ______

A Arithmetic mean B Geometric mean C Median D Percentile E Arithmetic mean and median

11. A set of variable values with sizes 13, 10, 12, 9, 8, 11, and 98 respectively. The median is ______

A 23 B 11 C 12 D 10 E 10.5

12． Serological antibody titer data, most often calculated as ______ to express its average level

A Arithmetic mean B Median C Geometric mean D Mean E Percentile

13. Normal distribution curve, when the population mean is constant, the larger the population standard deviation, _____

A. The further the curve moves to the left along the horizontal axis. B. The smaller the variation in the observed values, the steeper the curve.

C The greater the variation in the observed values, the flatter the curve. D The curve moves to the right along the horizontal axis.

The position and shape of the E curve remain unchanged

14.The standard normal distribution is _____

A Normal distribution with mean 0 and variance 1 B Normal distribution with mean 0 and variance 0

C is a normal distribution with a mean of 0 and a variance of any value. D is a normal distribution with a mean of any value and a variance of 1.

The position and shape of the E curve are not unique

15 Regarding the coefficient of variation, the following statement is correct: _____

A The coefficient of variation is the difference between the standard deviation and the mean B The coefficient of variation refers to the multiple of the mean as the standard deviation

C The unit of the coefficient of variation is the same as the original data. D The value of the coefficient of variation is generally negative.

E When comparing the variability of height and weight in the same population, it is appropriate to use the coefficient of variation

16. In sampling research, as the sample size gradually increases, _____

A The standard deviation gradually increases B The standard error gradually increases C The standard deviation tends to 0

D The standard deviation gradually decreases E The standard error gradually decreases

17. When using the t test to compare the means of two samples, when the difference is significant, the smaller the P, it means _____

A The difference between the means of the two populations is not big B The difference between the means of the two populations is greater

C The more reason there is to believe that the means of the two populations are very different D The more reason there is to believe that the means of the two populations are different

E The more reason there is to believe that the means of the two samples are different

18. The relationship between the t distribution and the normal distribution is _____.

A． They are all centered on 0 and symmetrical from left to right.　

B. When the overall mean increases, the center position of the distribution curve moves to the right.　　

C. The quantile points corresponding to the 5% areas at both ends of the curve are both plus or minus 1.96.　　　

D. As the sample size increases, the t distribution approaches the standard normal distribution.

E. The standard deviation is used to calculate the confidence interval, and the standard error is used to calculate the reference value range.

19.The variance of the standard normal distribution is equal to _____.

Ａ．0　Ｂ．1 Ｃ．1.64　Ｄ． 1.96 E．2.58

20. When comparing the means of two small samples, if the variances are uneven, you can choose

A t′ test B t test C F test D Chi-square test E u test

21. Under certain conditions of credibility, the following _____ can be used to reduce the width of the interval

A Increase the sample size B Replace the t bound with the u bound value C Resample according to the original sample size

D Remove observations with relatively large variability E None of the above are correct

22. Twelve women used two instruments to measure vital capacity to measure their maximum expiratory rate (L/min). If you want to compare the results of the two methods, you can do _____

A Grouped design u-test B Grouped design t-test C Paired design u-test

D Paired design t-test E Paired design chi-square test

23.The purpose of pairing design_____

A Easy to operate B Improve measurement accuracy C Easy calculation

D In order to use the t test E to improve comparability between groups

24. The denominator of the t test formula for paired measurement data comparison is _____

A The mean of the differences B The standard deviation of the differences C The standard error of the mean of the differences

D square root of the difference E variance of the difference

25. Statistical inference includes _____

A Statistical description and hypothesis testing B Parameter estimation and hypothesis testing C Statistical description and statistical analysis

D point estimate and interval estimate E calculate the mean and standard deviation

26. Which of the following statements about sampling error is correct?

ASampling errors are caused by inappropriate sampling methods

BThe difference between the sample mean and the population mean due to sampling reasons is called sampling error. Different samples are drawn from the same population, and the difference between sample means also reflects sampling error.

C. A sample is randomly selected. The sample mean minus the population mean is the sampling error.

D. Strictly following the randomization principle for sampling can avoid sampling errors.

E. In order to control sampling errors, the sample size should be expanded infinitely

27. A certain unit measured the height of 225 7-year-old boys in a survey. The variance is 144, then the standard error is _____

A 0.8 B 0.64 C 0.0533 D 1.56 E 1.96

28. A sample survey was conducted on the serum cholesterol (mmol/L) data of 100 healthy men. The calculated mean was 4.6000mmol/L and the standard deviation was 0.8392mmol/L. The standard error is _____

A 0.2654 B 0.0839 C 0.8392 D 0.0084 E 8.3920

29. An institute measured the cerebrospinal fluid magnesium (mmol/L) content of 36 tuberculosis patients and 28 healthy people, and found that the mean values of the samples were 1.04mmol/L and 1.28mmol/L respectively. For further research, the mean values of the two samples were There is no difference. Which of the following methods should be used?

A t-test for comparing the means of two small samples B U-test for comparing the means of two large samples

C t test for comparison of paired measurement data D t′ test E Correlation analysis

30. The coefficient of variation is an indicator that reflects the degree of variation. It belongs to _____

A rate B dynamic sequence C relative ratio D composition ratio E central tendency index

31. Regarding the discussion of relative numbers, which of the following statements is correct _____

A When calculating relative numbers, the number of examples in the denominator should not be too few. When the number of examples is small, the error in the calculation result will be larger. In this case, it is better to use absolute numbers.

B The composition ratio and rate are relative numbers, so their actual meanings are the same.

C If you want to combine two rates, just add the rates of each group and sum them up.

D Rate comparisons can be made between any data. E There is no sampling error in sample rates and composition ratios, and no statistical analysis is required.

32. From a statistical point of view, the following indicators are absolute numbers _____

A The number of people with acute infectious diseases in District A is 1.25 times that of District B. B The incidence rate of acute infectious diseases in District A in a certain year is 382/100,000.

C District A accounts for 18% of acute infectious diseases in a certain city D A man in a certain district is 168 cm tall

E The mortality rate of acute infectious diseases in District A in a certain year is 52.2/100,000

33. The number of people with hepatitis in a certain place in a certain year accounts for 14.9% of the number of infectious diseases in the same year. This indicator is ______.

A． Rate B. Composition ratio C. Incidence rate D. Prevalence E. infection rate

34. Regarding random sampling, which of the following statements is true_______.

Sampling should be done so that every individual in the population has an equal chance of being selected

Researchers should carefully select individuals when sampling so that the sample can be more representative of the population

Random sampling means randomly selecting individuals

To ensure a better representativeness of the sample, the sample size should be as large as possible

All the above statements are wrong

35. The value of the coefficient of variation is _______.

A. Must be greater than 1 B. Must be less than 1 C. It can be greater than 1 or less than 1　

D． Must be smaller than the standard deviation E. Must be larger than the standard deviation

36. For the chi-square test comparing two sample rates of data in a four-grid table, the correct one is _____

A Chi-square value is the mean value in the comparison of two sample rates.

B The larger the chi-square value, the more reason to reject the null hypothesis.

C The size of the chi-square value has nothing to do with the sample size

D The difference between the theoretical frequency and the actual frequency of each grid is equal

E Chi-square test can only be used for one-sided tests

37. The degree of freedom of row × list is _____

A Number of rows-1 B Number of columns-1 C Number of rows × number of columns D (Number of rows-1) × (Number of columns-1) E Sample size-1

38. When comparing four percentages, if one theoretical number is less than 5 and the others are greater than 5, then _____

A. Only the adjusted chi-square test can be done. B. The chi-square test cannot be done. C. No correction is required for the chi-square test.

D must do a reasonable merge first. E can only do the rank sum test.

39. The basic numbers of the four grids in the four-square table are _____

A The numerator and denominator of two sample rates B The numerator and denominator of two constituent ratios

C Two pairs of actual positive and negative numbers D A set of absolute numbers and a set of theoretical numbers

E Four sample rates or four composition ratios

40. The four-grid chi-square test can be used to _____

A Hypothesis test for the difference between two means B Hypothesis test for the comparison of two medians

C Hypothesis test for comparison of two sample rates D Hypothesis test for comparison of sample rate and population rate

E Hypothesis test comparing sample mean with population mean

41. Row×list chi-square test, if the probability P is less than 0.05, then _____

A Multiple population rates (or composition ratios) are different from each other B Multiple population rates (or composition ratios) are different

C At least two population rates (or composition ratios) are different. D All population rates (or composition ratios) are equal.

E At least two sample rates (or sample composition ratios) are not equal

42. For the chi-square test on data with 4 sample rates with a total total n of 400, the degree of freedom is _____

A 399 B 396 C 1 D 4 E 3

43. In the signed rank test of differences for paired comparisons, if two differences are 0, then _____

A has 0.5 and 1 for positive rank sums, -0.5 and -1 for negative rank sums B has 2 for positive rank sums, and -2 for negative rank sums

C There is 3 for the positive rank sum, and -3 for the negative rank sum. D There is 1.5 for the positive rank sum, and -1.5 for the negative rank sum. E 0 is discarded.

44． The advantage of the rank sum test is _____

A. The probability of making judgment errors is small. B. It is not limited to the distribution type. C. It is suitable for comparing the means of two groups.

D Suitable for comparison of two rates E Make full use of sample information

45. Paired signed rank test, if the null hypothesis is true, then for the sample _____

A The absolute value of the positive rank sum is smaller than the absolute value of the negative rank sum B The absolute value of the positive rank sum is greater than the absolute value of the negative rank sum

C The absolute value of the positive rank sum is equal to the absolute value of the negative rank sum D The absolute values of the positive and negative rank sums will not differ greatly

E The absolute values of positive and negative rank sums are very different

46. A doctor planned to study the difference in health care knowledge levels among five professions. According to regulations, the health care knowledge levels were divided into four levels. A total of 400 subjects were surveyed by random sampling, and the rank sum test was used in the analysis. , the critical value should be checked in the chi-square value table, and its degrees of freedom should be _____

A 399 B 5 C 4 D 12 E 20

47. In the signed rank test of paired design, if the absolute value is non-zero and the same difference is encountered, the ranking should be _____

A discard and ignore B rank in order C take its average rank D take its maximum rank E take its minimum rank

48. In the linear regression analysis, the regression coefficient was 0.30, which was statistically significant after testing, indicating that

A Y increases by one unit, X decreases by 30% on average

B X increases by one unit, Y decreases by 30% on average

C X increases by one unit, Y decreases by 0.30 units on average

D Y increases by one unit, X decreases by 0.30 units on average

When E X increases by one unit, Y increases by an average of 0.30 units.

49. The applicable range of the linear regression equation is generally limited to the value range of _______.

A. Independent variable X B. Dependent variable Y C. Average estimated value of Y D. Average value of X E Average value of Y

50. Hypothesis testing of linear correlation coefficient, its degrees of freedom are

A n B n-1 C n-2 D 2n-1 E 2n-2

51. According to the observation results, the regression equation 3+5.0x of Y on X has been established. If X changes by 1 unit, Y will change by ____ units on average?

A 1 B 2 C 3 D 4 E 5

52. Which of the following statistical charts must have “0” as its starting point?

A Scatter graph B Semi-logarithmic line graph C Line graph D Bar graph E Circle graph

53. The graph shows the rate of increase and decrease in the incidence of three diseases in each year since liberation in a certain area. It should be drawn

A Ordinary line graph B Histogram C Composition ratio bar graph D Semi-logarithmic line graph E Histogram

54. Which of the following descriptions of bar graphs is correct?

The A-bar graph uses the length of equal-width straight bars to represent the value of the continuous statistical index.

B The straight bars on the horizontal axis are generally arranged from large to small according to statistical indicators, or they can also be arranged in natural order.

C The scale of the vertical axis usually starts from zero, but it does not need to start from zero.

D The width of each straight bar is different

E The vertical and horizontal axis ratio is 5:9

55. When drawing statistical tables, the correct option is

A. The title is usually placed below the table. B. If the number is temporarily missing, it can be represented by spaces.

C. The title should include all contents such as remarks. D. In addition to the top line and bottom line, slashes can also be used.

E The combination of vertical and horizontal headings expresses a complete meaning

56. It is suitable to express the dependence between two numerical variables using

A Histogram B Circle graph C Bar graph D Percent bar graph E Scatter graph

57. The graph shows the changing trend of the incidence of typhoid fever from 1991 to 1998. It should be drawn

A Bar graph B Composition graph C Line graph D Scatter graph E Histogram

58. Chi-square distribution, t distribution, and normal distribution each have ______ parameters.

A. 1，1，1 B. 2，2，2 C. 1，1，2 D . 2，2，1 E 1，2，1

59. In the signed-rank test of paired design data, the null hypothesis is ____.

A. The population mean of the difference is equal to 0 B. The population median of the difference is equal to 0 C. The population mean of the difference is not equal to 0 D. The population median of the difference is not equal to 0 E The sample mean of the difference number equals 0

60. The principle of using the least squares method to determine the linear regression equation is _____.

A. The longitudinal distance of each observation point from the straight line is equal. B. The sum of the squared longitudinal distances of each observation point from the straight line is the smallest.

C. The vertical distance between each observation point and the straight line is equal. D. The sum of squares of the vertical distances between each observation point and the straight line is the smallest.

E. The longitudinal distance between each observation point and the straight line is the smallest

2. Fill in the blanks

1. Types of statistical data can be divided into ⑴ and ⑵.

2. Two important parameters of the normal distribution are ⑶ and ⑷.

3． The types of frequency distribution of medical data include ⑸ and ⑹.

4. If a certain quantitative indicator is too low and is abnormal, and the data is skewed, its 95% medical reference value range is ⑺.

5. Under the normal curve, the area contained by (⑻, ⑼) is 95.00%.

6. The principle for determining the parameters of the linear regression equation is ⑽.

7. Measurement data can be divided into ⑾ and ⑿.

8. Indicators describing the central tendency of measurement data include ⒀, ⒁ and ⒂.

9. The indicators describing the discrete trend of measurement data are ⒃, ⒄, ⒅, ⒆ and ⒇.

10. The number of people with tuberculosis in a certain place in a certain year accounts for 6% of the number of infectious diseases in the same year. This indicator is ⑴.

11. The statistic that measures the sampling error of the sample mean is ⑵.

12. The combination of ⑶ and ⑷ is a complete statistical description of normally distributed data.

13. The combination of ⑸ and ⑹ is a complete statistical description of skewed distribution data.

14. The mean of the standard normal distribution is ⑺ and the variance is ⑻.

15. The two elements of the confidence interval are ⑼ and ⑽.

16. The application conditions of u test are ⑾ and ⑿.

17. For two small samples with normal distribution but uneven variances, the ⒀ test is suitable for the mean test.

18. The analysis steps of simple linear regression are ⒁, ⒂ and ⒃.

19. Statistical tables can be divided into ⒄ and ⒅.

20. Parameter estimates include ⒆ and ⒇.

3. Explanation of terms

1. Population 2. Sample 3. Parameter 4. Statistics 5. Sampling error 6. Regression coefficient 7. Correlation coefficient 8. Medical reference value range 9. Variation 10. Probability 11. Sample size 12. Quantitative data 13. Positive skewness Distribution 14. Negatively skewed distribution 15. Median 16. Percentile 17. Statistical inference 18. Standard error 19. Parameter estimation 20. Point estimation 21. Interval estimation 22. 95% confidence interval meaning 23. Class I Error 24. Type II error 25. Test power 26. Parametric test 27. Non-parametric test 28. Rate 29. Constituent ratio 30. Relative comparison

4. Short answer questions

1. Briefly describe the precautions when applying relative numbers.

2. Briefly describe the applications of normal distribution.

3. Briefly describe the meaning of the medical reference value range and write down two calculation methods and formulas for the 95% bilateral medical reference value range.

4. Briefly describe the scope of application of rank correlation.

5. Briefly describe the precautions for hypothesis testing.

6. Briefly describe the characteristics of normal distribution.

7. Briefly describe the main uses of frequency tables.

8. Briefly describe the purpose of the standardization method and the calculation formula of the standardization rate.

9. In the calculation of standardized rate, what are the methods for selecting the standard group?

10. Briefly describe the characteristics of t distribution.

11. Briefly describe the application scope of the rank sum test.

12. Briefly describe the application of linear regression.

5. Analyze calculation problems

1. A city collected height frequency distribution data of 120 5-year-old girls (see Table 1). (Total 20 points)

Table 1 Frequency distribution of height of 120 5-year-old girls

Group segment/cm frequency

95～ 1

98～ 7

101～ 10

104～ 18

107～ 25

110～ 21

113～ 15

116～ 15

119～ 7

122～125 1

Total 120

question:

(1) Please indicate the data type and frequency distribution type of this question, and briefly describe the characteristics of the frequency distribution type in Table 1

(6 points)

(2) What indicators are suitable for describing the concentration and dispersion trends in this data? And find the specific values. (4 points)

(3) Try to estimate the possible range of the average height of 5-year-old girls in the city and explain its meaning (5 points).

(4) Try to estimate the possible range of heights for 95% of 5-year-old girls in the city and explain its meaning (5 points).

2. The information collected by a researcher is shown in Table 2 (total 20 points)

Table 2 Relationship between types of leukemia and blood types

leukemia

type

blood type

total

acute

184

Chronic

total

111

101

295

question:

(1) What type of statistical data is in Table 2? What are the three types of indicators commonly used to describe this type of data? (4 points)

(2) What should we pay attention to when using the above three types of indicators to describe data? (5 points)

(3) Which statistical method is suitable for analyzing the data in Table 2 (whether there is a difference in blood type composition between patients with acute and chronic leukemia). Please write down the specific hypothesis testing process and briefly describe the precautions for this testing method (11 points) (Chi-square bound is 7.81)

3. A scholar studied the data of apolipoprotein B (X, mg/dl) and low-density lipoprotein (Y, mg/dl) as follows: (Total 20 points)

Sample number: 1 2 3 4 5 6 7 8 9 10

Apolipoprotein B (X): 106 132 112 138 94 160 154 141 137 151

Low-density lipoprotein (Y): 137 162 134 188 138 215 171 148 197 113

question:

(1) When performing linear regression analysis, what steps should be followed to avoid making statistical errors (3 points)

(2) How to describe the dependence of Y on X? Please write the expression (12 points)

(3) If the data does not obey the bivariate normal distribution, what statistical index should be used to analyze the correlation between the two variables? Request the indicator value. (5 points)

Statistics test questions (1) and their answers

1. Multiple choice questions (2 points for each question, 20 points in total)

1. The quantitative characteristics of socioeconomic statistics are shown in ( ).

A. It is a purely quantitative study

B. It starts from the study of the quantity of things to understand the essence of things

C. It starts from qualitative understanding and ends with quantitative understanding.

D． It studies the quantitative aspects of social and economic phenomena in the relationship between quality and quantity.

2. If a certain survey is repeated continuously and the same question is asked to 100 randomly selected people each time, then one person who answers "yes" will get hundreds of points each time. The distribution of these percentages is called: ().

A. The frequency distribution of the population mean B. The sampling distribution of the sample mean

C. The frequency distribution of the population D. Sampling distribution with a number of samples

3． When the frequency of each variable value in the variable sequence is equal ( ).

A. The mode of the sequence is equal to the median B. The mode of the sequence is equal to the mean

C. This sequence has no mode D. The mode is equal to the largest value

4. Among the measures that describe the degree of data dispersion, ( ) is the most commonly used.

A. Full range B. mean difference

C. Standard deviation D. standard deviation coefficient

5. To calculate the sampling error of equally spaced sampling of unrelated marks, generally approximate ( ).

A. Error formula for multi-stage sampling B. Error formula for simple random sampling

C. Error formula for stratified sampling D. Error formula for cluster sampling

6. Comprehensive comparison of the price levels of property management fees in the two cities during the reporting period, it belongs to ( ).

A. Relative intensity number B. dynamic relative number

C. Structural impact index D. static index

7. If the sales of goods in a certain area increase by 5% and the average retail price of goods increases by 2%, the sales volume of goods will increase ( ).

A．7% 　　　 B．10% 　　　C．2.94% D．3%

8. For the linear regression square city Y=a+bx established between two variables with a linear correlation, the regression coefficient b ( ).

A. It must be a positive number 　　B. Significantly not 0

C. Possibly 0 　　 D. Definitely a negative number

9. If product output increases and production costs remain unchanged, the unit product cost index ( ).

A. Rising B. Decline C. Unchanged D. uncertain

10. Which of the following phenomena has a chivalrous correlation coefficient ( ).

A. Interest rates and interest on time deposits B. Sales volume and sales price of a certain product

C. Resident income and commodity sales D. TV production and food production

2. Multiple-choice questions: (3 points for each question, 15 points in total)

1. Major issues in inferential statistics research ( ).

A. How to scientifically determine the overall scope of goals B. How to scientifically sample from a population

C. How to control the representative error of the sample to the population D. How to eliminate the error of sample representativeness of the population

E. How to scientifically infer the population from the sampled books

2. If foreign net factor income is a positive number, the correct quantity relationship is ( ).

A. Gross National Income>Gross Domestic ProductB. Gross Domestic Product > Gross National Income

C. Gross Domestic Product >Net National Income D. Net National Income > Gross Domestic Product

　E． Gross Domestic Product >Net National Income

3． When compiling the comprehensive method index, the functions of the same measurement factors are ( ).

A. Balancing effect B. Same measurement effect C. weight function

D． Average effect E. Comparative effect

4. In hypothesis testing, when we make the observation value of the test statistic to fall into the rejection region of the null hypothesis, it means ( ).

A. There is no sufficient reason to reject the null hypothesis B. The null hypothesis is established

C. You can safely trust the null hypothesis D. The P value of the test is large

E. If the null hypothesis is rejected, the probability of making a Type I error exceeds the allowed limit.

5. Compared with last year, the total price index of various commodities of a commercial enterprise was 117.5% this year. This result shows ( ).

A. Retail prices of commodities increased by an average of 17.5% B. Retail sales of goods increased by 17.5%

C. Retail sales increased 17.5% due to higher prices

D． Retail sales decreased by 17.5% due to higher prices

E. Retail sales of goods increased by 17.5%

3. Simple Expression Questions (30 points in total)

1. Briefly describe the functions of statistics

2. Briefly describe the good standards of sampling estimation

3． Briefly describe seasonal fluctuations and their characteristics

4. Briefly describe several factors that affect sampling average error

5. Briefly describe the contents of correlation and regression analysis

4. Calculation questions: (35 points in total)

1. The mathematics scores of a certain class are as follows:

2. There are 3,000 day students in a university. The school's logistics department wants to estimate the average time it takes these students to go back and forth every day. Estimate with a confidence interval of 95% confidence, and make the estimated value within an error range of 1 minute near the true value. A previously sampled small sample gives a standard deviation of 4.8 minutes. How large a sample should be taken?

3． A person in charge wants to estimate the length of 6,000 parts, and randomly selects 350 parts. The test results are that the average length is 21.4mm, and the sample standard deviation is 0.15mm. Try to find a 95% confidence interval for the overall mean u?

Statistics test questions and answers

1. Multiple choice questions:

1——6: DDCBB

6——10: DCBBC

2. Multiple choice questions:

11——15: BCE， AD， BC， ADE， AC

3. Short answer questions:

1. Statistics is an important part of the modern national management system. Its main functions are to provide information, conduct consultation, and implement supervision. That is to say, statistics has three major functions: information, consultation, and supervision.

2. (1) Unbiasedness: means that the average of the sample indicators is equal to the estimated overall indicator.

(2) Validity: When using sample indicators to estimate the overall indicator, if the variance of a certain sample indicator is smaller than the variance of other estimators, then the sample indicator is said to be the most effective estimator of the overall indicator.

(3) Consistency: Using sample indicators to estimate the overall indicator requires that when the number of sample units is quite large and the sample indicator is sufficiently close to the overall indicator, then this estimator is called a consistent estimator.

3. Seasonal fluctuations refer to certain social and economic phenomena, which are caused by repeated changes in time within a certain period (usually one year) due to the influence of seasonal natural factors and social factors.

Seasonal fluctuations generally have three basic characteristics: (1) Seasonal fluctuations have certain regularity and periodicity. (2) Seasonal fluctuations recur every year and are repetitive. (3) The fluctuation trajectories of seasonal fluctuations are similar.

4. (1) The degree of difference in marker values between overall units

(2) Number of sample units

(3) Sampling method

(4) Sampling organizational form

5. Correlation and regression analysis is a statistical method for analyzing the correlation between objective social and economic phenomena. Its purpose is to quantitatively infer and understand the dependencies between phenomena and the regularities they exhibit in order to make predictions and decisions. The content of correlation and regression analysis can be divided into two parts, namely correlation analysis and regression analysis. Correlation analysis is an analysis that studies the correlation and closeness between two or more variables. It specifically includes two aspects: judging whether there is a correlation between phenomena; judging the manifestation and closeness of the correlation. To judge the correlation and its closeness, you can generally conduct qualitative and quantitative analysis, compile relevant charts, and calculate correlation coefficients and other indicators to reflect the direction and closeness of the correlation.

4. Calculation questions:

The answer is a bit….

0907 "Principles of Statistics" test questions and answers

1. Multiple-choice questions (2 points for each question, 12 points in total)

1. The individual things that constitute the statistical population are called (c).

A. Survey population B. Survey unit C. Overall unit D. Flag value

2. The submission time for the 2007 annual report on production and operation results of an industrial enterprise in a certain city is set on January 31, 2008, so the investigation period is (B).

A. One day B. One month C. One year D. One year and one month

3. The basis for dividing comprehensive investigation and non-comprehensive investigation is (B).

A. The size of the survey organization B. Whether the units included in the survey objects are complete

C. Is the final investigation data obtained comprehensive? D. Is the investigation time continuous?

4. The indicator that directly reflects the overall size is (A).

A. Total index B. Relative index C. Average index D. Variation index

5. Sampling error refers to (C).

A. Registration errors arising from the survey B. Systematic errors arising from the survey

C. Random representative error D Error generated during the calculation process

6. If the correlation coefficient between variable X and variable Y is 1, it means that there is (C) between the two variables.

A. Weak correlation B. Significant correlation

C. Complete correlation D. No correlation

2. Multiple choice questions (2×4=8 points)

1. In the investigation of production equipment of industrial enterprises (BCE).

A. All industrial enterprises are the objects of investigation

B. All production equipment of industrial enterprises are the objects of investigation

C. Each piece of equipment is an investigation unit

D. Each piece of equipment is both an investigation unit and a reporting unit.

E. Each industrial enterprise is a reporting unit

2. Which of the following groups are grouped by quality mark (BCDE)?

A. Employees are grouped according to length of service B. Scientific and technical personnel are grouped according to professional titles

C. Population is grouped by ethnicity D. Enterprises are grouped by economic type

E. Population is grouped by region

3. The variation index can be calculated (BDE).

A. Reflects the central tendency of the overall distribution of marker values in each unit

B. Reflects the deviation trend of the overall distribution of each unit's mark value.

C. Analyze the dependencies between phenomena

D. Measuring the representativeness of the average

E. Explain the uniformity or stability of the phenomenon changes

4. The two calculation forms of the total index are (BC).

A. Individual index B Comprehensive index C Average index D Fixed base index E Chain index

3. True or False Questions (2×5=10 points)

1. The research object of statistical work is the quantitative aspect of the overall objective phenomenon. (√)

2. The variation index and the average index reflect the overall characteristics from different aspects. Therefore, the larger the value of the mark variation index, the higher the representativeness of the average index, and conversely, the lower the representativeness of the average index. (× )

3. Comprehensive investigation includes census and statistical reports. (× )

4. A survey in a certain area revealed that there are 54 doctors per 10,000 people in the area. This indicator is a strength relative indicator. (√)

5. It is known that the chain growth rates in each period are 3%, 2%, 7% and 5%, then the corresponding technical method of fixing the base growth rate is 3%×2%×7%×5%-100%. (×)

5. Calculation questions

1. The price, sales volume and sales data of a certain commodity in markets A and B in a certain month of 2008 are as follows:

Variety

Price (yuan/piece)

A market sales volume

B market sales (yuan)

First

Second

105

120

137

700

900

1100

126000

96000

95900

total

——

2700

317900

Try to calculate the average price of the commodity in the two markets.

Solution: The average price in market A is:

The average price in market B is

2. From a batch of finished products, 100 pieces were selected using the repeated sampling method, of which 4 were scrap. When the probability is 95.45%, can it be considered that the scrap rate of this batch of products does not exceed 6%?

untie:

It cannot be considered that the scrap rate of this batch of products does not exceed 6%

3. The survey data on the cost reduction rate (%) and sales profit (10,000 yuan) of comparable products of 20 companies affiliated to a certain department are compiled as follows (representing the cost reduction rate of comparable products, sales profit is):

Requirements: (1) Try to establish a linear regression equation of sales profit according to the cost reduction rate of comparable products. When the cost reduction rate of comparable products is predicted to be 8%, how many million yuan will the sales profit be?

(2) Explain the economic meaning of the regression coefficient in the formula

Solution: (1) Cooperate with the linear regression equation

(2) Economic meaning of regression coefficient b

The cost reduction rate of comparable products increased by 1%, and sales profits increased by an average of 143,300 yuan.

January 2008 "Principles of Statistics"

1. Multiple choice questions

1. The individual things that constitute the statistical population are called (c).

A. Survey population B. Survey unit C. Overall unit D. Flag value

2. When grouping, whenever the flag value of a certain unit is exactly equal to the upper and lower limits of two adjacent groups, it is usually (A).

A. Put this value into the upper limit group B. Put this value into the lower limit group

C. This value can be classified into two groups. D. Create another group.

3. When calculating the structural relative index, the sum of the proportions (C) obtained by comparing the values of each part of the whole with the overall value.

A. Less than 100% B. Greater than 100% C. Equal to 100% D. Less than or greater than 100%

4.The investigation time refers to (A).

A. The time the survey data belongs to B. The time the survey was conducted

C. Duration of investigation work D. Time for delivery of investigation materials

5. The indicator that directly reflects the overall size is (A).

A.Total index B.Relative index C.Average index D.Variation index

6. If prices rise and the demand for goods decreases, the relationship between prices and demand for goods is (B).

A. Uncorrelated B. Negatively correlated C. Positively correlated D. Complexly correlated

2. Multiple choice questions

7. In the National Census (BCE).

A. The total population of the country is a statistical population B. Men are a symbol of quality

C. A person's age is a variable D. Each household is an overall unit

E. The average age of the population is a statistical indicator

8. Which of the following groups are grouped by quality mark (BCDE).

A. Employees are grouped by age B. Scientific and technical personnel are grouped by professional title

C. Population is grouped by gender D. Enterprises are grouped by region

E. Students are grouped according to health status

9. Under which of the following conditions, the weighted arithmetic mean is equal to the simple arithmetic mean (ADE).

A. The number of times in each group is equal B. The variable values in each group are unequal C. The variable array is a group distance sequence

D. The number of reps in each group is 1. E. The number of reps in each group accounts for an equal proportion to the total number of reps.

10. In dynamic sequence analysis, the indicators that reflect changes in the speed of phenomena are (BDE).

A. Development level B. Development speed C. Average development level

D. Average development speed E. Growth amount and average growth amount

3. Judgment questions

11. In practical applications, to calculate the price comprehensive index, it is necessary to use the base period quantity indicator as the same measurement factor. (×)

12. In a certain year, the ratio of retail sales of social commodities in places A and B is 1:3. This is a relative indicator of proportion. (×)

13. Investigate the main food crop producing areas in my country to understand the basic situation of the growth of main food crops in the country. This kind of investigation is a key investigation. (√)

14. The average development speed is the average of the chain development speed, and it is also a sequential average. (√)

15. The distribution sequence formed by grouping by quantity mark and the distribution sequence formed by grouping by quality mark can both be called frequency distribution. (√)

4. Short answer questions

16. Give examples to illustrate the difference between logos and logo representations.

17.What are the main contents of a complete statistical survey plan?

5. Calculation questions

18. Classes A and B took the test of the "Principles of Statistics" course at the same time. The average score of Class A was 81 points, and the standard deviation was 9.5 points; the score grouping information of Class B is as follows:

Group by grade

Number of students (people)

60 or less

60—70

70—80

80—90

90--100

Calculate the average score of students in Class B and compare the average score of Class A and Class B. Which class is more representative?

Solution: The average grades of students in Class B, the required calculation data are shown in the table below:

Group by grade

Number of students (people)

group median

60 or less

60—70

70—80

80—90

90--100

220

650

1875

1190

190

-20

-10

400

100

400

1600

1000

1400

8000

total

——

4125

132

(To compare the average scores of Class A and Class B, which one is more representative, the coefficient of variation should be compared.)

Class A

From the calculation results, we know that the coefficient of variation of Class A is small, so the average score of Class A is more representative.

19. The total cost and output data of a company’s products are as follows:

product

name

Total cost (10,000 yuan)

Yield Growth Individual Yield Index

(%) K（%）

Base period

Reporting period

First

Second

100

120

20 120

2 102

5 105

Calculate (1) the overall product output index and the total cost increased due to output growth.

(2) Total cost index and absolute amount of total cost increase or decrease.

Solution; (1) The total product output index is:

Total cost increase due to increased production:

(2) The total cost index is:

Absolute amount of increase or decrease in total cost:

20. The monthly merchandise sales and month-end inventory data of a department store are as follows:

March

April

May

June

Sales (10,000 yuan)

150

200

240

276

Inventory amount (10,000 yuan)

Calculate the average monthly number of commodity circulation in the second quarter and the number of commodity circulation in the second quarter.

Solution: Number of product circulation c = product sales a/inventory amount b

Product sales constitute a period sequence, so

The inventory amount b constitutes a sequence of time points with equal intervals, so

The average number of monthly merchandise flows in the second quarter

Number of commodity circulation in the second quarter 3*4.475=13.425

July 2008 "Principles of Statistics" test questions

1. Multiple choice questions (2 points for each question, 12 points in total)

1. The individual things that constitute the statistical population are called (D).

A. Survey unit B. Mark value C. Quality mark D. Overall unit

2. Which of the following groups is grouped according to the quantity mark (A).

A. Enterprises are grouped by annual production capacity. B. Enterprise workers are grouped by gender.

C. Population is grouped by ethnicity D. Families are grouped by town

3. The basis for dividing comprehensive investigation and non-comprehensive investigation is (B).

A. The size of the survey organization B. Whether the units included in the survey objects are complete

C. Is the final information obtained comprehensive? D. Is the investigation time continuous?

4. The indicator obtained by summarizing the sign values that reflect the quantitative characteristics of each unit in the population is (B).

A. Overall unit total B. Overall mark total C Relative index D Average index

5. Sampling error refers to (C).

A. Registration errors produced in the survey B. Systematic errors produced in the survey

C. Random representative errors D. Errors generated during the calculation process

6. The basis for dividing the quantitative index index and the quality index index is (A).

A. The nature of the index index is different. B. The scope of the objects reflected is different.

C. The characteristics of the phenomena being compared are different. D. The methods of compiling the index are different.

2. Multiple choice questions (2 points for each question, 8 points in total)

1. In the investigation of production equipment of industrial enterprises (BCE).

A. All industrial enterprises are the objects of investigation

B. All production equipment of industrial enterprises are the objects of investigation

C. Each production equipment is an investigation unit

D. Each production equipment is both an investigation unit and a reporting unit.

E. Each industrial enterprise is a reporting unit

2. Which of the following groups are grouped by quality mark (BCDE)?

A. Employees are grouped by age B. Scientific and technical personnel are grouped by professional title

C. Population is grouped by ethnicity D. Enterprises are grouped by economic type

E. Population is grouped by region

3. The variation index can be calculated (BDE).

A. Reflects the central tendency of the overall distribution of marker values in each unit

B. Reflects the deviation trend of the overall distribution of each unit's mark value.

C. Analyze the dependencies between phenomena

D. Measuring the representativeness of the average

E. Explain the uniformity or stability of the phenomenon changes

4. The two calculation forms of the total index are (BC).

A. Individual index B. Comprehensive index C. Average index

D. Fixed base index E. Chain index

3. True or False Questions (2 points for each question, 10 points in total)

1. The survey unit of my country’s census is “person” and the reporting unit is “household”. (√)

2. The key to statistical grouping is to determine the group limits and distances. ( × )

3. The larger the value of the marker variation index, the less representative the average index is. (√)

4. The average index is an important form of the total index and has its own independent application significance. (√)

5. The level of development is the value of each specific indicator in the dynamic sequence, and its expression can only be an absolute number. ( × )

4. Short answer questions (10 points for each question, 20 points in total)

1. Give an example to explain how to understand the relationship between the survey unit and the reporting unit?

2. Briefly describe the difference between structural relative indicators and proportional relative indicators and give examples.

5. Calculation and analysis questions (required to write down formulas and calculation processes, and keep the results to two decimal places. This question is worth 50 points in total)

1. The number of parts (pieces) processed per day by 30 workers in a production workshop is as follows:

30 26 42 41 36 44 40 37 37 25

45 29 43 31 36 36 49 34 47 33

43 38 42 32 34 38 46 43 39 35

Requirements: (1) Divide the above data into the following groups: 25-30, 30-35, 35-40, 40-45, 45-50, calculate the frequency and frequency of each group, and compile a frequency distribution table;

(2) Calculate the average daily number of parts produced by workers based on the finishing table. (20 points)

Solution: (1) Based on the above data, prepare the frequency distribution table as follows:

Grouping by number of parts processed per worker day (pieces)

Number of workers (frequency)

frequency%

25—30

30—35

35—40

40—45

45—50

26.67

13.33

total

100

(2) The required calculation data are shown in the table:

Grouping by number of parts processed per worker day (pieces)

group median

Number of workers (frequency)

Total number of parts processed

25—30

30—35

35—40

40—45

45—50

27.5

32.5

37.5

42.5

47.5

82.5

195

337.5

340

190

total

———

1145

Then the average labor productivity of workers is:

2. The product output and unit cost data of a company in the second quarter are as follows:

month

Output (thousand pieces)

Unit cost (yuan)

Requirements: (1) Establish a linear regression equation with output as the independent variable. Point out what is the average change in unit cost when output increases by 1,000 pieces?

(2) When the output is 10,000 pieces, how much is the predicted unit cost? (15 marks)

Solution: (1) The required calculation data are shown in the table below:

month

Yield

unit cost

219

276

340

total

210

835

Because, when the output increases by 1,000 pieces, that is, when it increases by 1 unit, the average change in unit cost is: an average decrease of 2.5 yuan

(2) When the output is 10,000 pieces, immediately, the unit cost is

Yuan

3. A company produces two products, A and B. The output and unit cost data for the base period and the reporting period are as follows:

product

Output (pieces)

Unit cost (yuan/piece)

base period

reporting period

base period

reporting period

First

Second

1000

3000

1100

4000

Try to find (1) the total output index and the total unit cost index;

(2) Total cost index and total cost changes. (15 marks)

Solution: (1) The total output index is

Overall unit cost index

(2) Total cost index = total output index * total unit cost index

=126.47%*95.81%=121.17%

(or total cost index = )

total cost change

January 2009 Principles of Statistics Test Questions (Central Radio and Television University)

Multiple choice questions (2×6=12 points)

1. The individual things that constitute the statistical population are called (D).

A. Investigating unit B. Mark value C, quality mark D, overall unit

2. The submission time for the 2007 annual report on production and operation results of an industrial enterprise in a certain city is set on January 31, 2008, so the investigation period is (B).

A. One day B. One month C. One year D. One year and one month

3. The basis for dividing comprehensive investigation and non-comprehensive investigation is (B).

A. The size of the survey organization B. Whether the units included in the survey objects are complete

C. Is the final investigation data obtained comprehensive? D. Is the investigation time continuous?

4. The indicator that directly reflects the overall size is (A).

A. Total index B. Relative index C. Average index D. Variation index

5. Sampling error refers to (C).

A. Registration errors arising from the survey B. Systematic errors arising from the survey

C. Random representative error D Error generated during the calculation process

6. If the correlation coefficient between variable X and variable Y is 1, it means that there is (C) between the two variables.

A. Weak correlation B. Significant correlation

C. Complete correlation D. No correlation

Multiple choice questions (2×4=8 points)

1. In the industrial census, (BE).

A. The total number of industrial enterprises is the statistical population. B. Each enterprise is a statistical unit.

C. The total amount of fixed assets is a statistical population. D. The number of enterprise equipment is a continuous variable. E. The number of enterprise employees is a discrete variable.

2. Which of the following groups are grouped by quality mark (BCDE)?

A. Employees are grouped according to length of service B. Scientific and technical personnel are grouped according to professional titles

C. Population is grouped by ethnicity D. Enterprises are grouped by economic type

E. Population is grouped by region

3. The factors that affect the size of sampling error are (ABCD).

A. Organizational form of sampling survey B. Method of selecting sample units

C. The degree of variation of the overall studied marker D. The number of sample units drawn

E. Attributes of the overall studied mark

4. The two calculation forms of the total index are (BC).

A. Individual index B Comprehensive index C Average index D Fixed base index E Chain index

True or False Question (2×5=10 points)

1. Quality indicators are expressed in relative numbers or averages. (√)

2. The key to statistical grouping is to determine the number of groups and the distance between groups. ( × )

3. The larger the value of the marker variation index, the less representative the average index is. (√)

4. The average index is an important form of the total index and has its own independent application significance. (√)

5. Growth amount = reporting period level – base period level, so the growth amount cannot reflect the speed of development and change of the phenomenon. ( × )

Short answer questions (10×2=20 points)

Give an example of how statistical signs differ from sign representations?

Briefly describe the types and application conditions of variable grouping.

Calculation and analysis questions (required to write down formulas and calculation processes, and keep the results to two decimal places. 50 points in total)

1. The number of parts (pieces) processed per day by 30 workers in a production workshop is as follows:

30 26 42 41 36 44 40 37 37 25

45 29 43 31 36 36 49 34 47 33

43 38 42 32 34 38 46 43 39 35

Requirements: (1) Divide the above data into the following groups: 25-30, 30-35, 35-40, 40-45, 45-50, calculate the frequency and frequency of each group, and compile a frequency distribution table;

(2) Calculate the average daily number of parts produced by workers based on the finishing table. (20 points)

Solution: Same as the July 2008 "Principles of Statistics" test questions 5.1.

2. There are 5,000 rural households in a certain township, and 100 households were repeatedly selected for investigation based on the random principle. The average annual net income of each household was 12,000 yuan, with a standard deviation of 2,000 yuan. Require:

(1) Estimate the average annual net income range of each household in the township based on 95% probability (Z=1.96).

(2) Estimate the range of the total annual net income of rural households in the township with the same probability. (15 points)

untie:

(1) Estimate the average annual net income range of each household in the township based on 95% probability (Z=1.96)

(Tip: The average annual net income per household, the average annual net income per household in the township, the range:, and)

Therefore, based on the 95% probability (Z=1.96), it is estimated that the average annual net income range of each household in the township is: 11,608-12,392 yuan.

(2) With the same probability, the range of the total annual net income of rural households in the township is estimated as:

(Tip: The range of the average annual net income of each household in the township is: , there are households, so the range of households is)

That is 5000*11608-5000*12392 yuan, that is

58.04 million yuan - 61.96 million yuan

The data on sales volume and price increase of three commodities sold by a group company are as follows:

merchandise

type

unit

Product sales (10,000 yuan)

Price increase % individual price index (%)

base period

reporting period

First

Second

strip

pieces

piece

2 102

5 105

0 100

Try to find the total price index and the total sales index. (15 marks)

Solution: General price index:

Total sales index:

January 2007 "Principles of Statistics" test questions

Multiple choice questions

1. Which of the following groups is grouped by quality mark (C)

A. Students are grouped according to test scores B. Enterprises are grouped according to the degree of completion of the plan

C. Products are grouped by variety D. Households are grouped by annual income level

2. A sign is a name that describes the characteristics of an overall unit (A)

A. It is divided into two categories: quality mark and quantity mark. B quality mark has mark value.

C. The quantity index has a mark value. D. Both the quality mark and the quantity mark have a mark value.

3． The value range of the correlation coefficient is (C)

A B﹤﹤1 C D

4. Under certain sampling average error conditions (A)

A Expanding the limit error range can improve the reliability of inference

BExpanding the limit error range will reduce the reliability of the inference

C narrowing the limit error range can improve the reliability of inference

D narrows the limit error range without changing the reliability of the inference

5. Two variables in regression analysis (D)

A is a random variable and B is equivalent.

C is a given quantity. D is an independent variable and the other is a dependent variable.

6. To conduct quality inspection on a batch of goods, the most appropriate method is (B)

A comprehensive survey B sample survey C typical survey D focused survey

2. Multiple choice questions

1. What sample surveys and focused surveys have in common is (AB)

A. Both are non-comprehensive surveys. B. The selected units of both are not affected by subjective factors.

C Both select units based on random principles D Both select units based on non-random principles

EBoth can be used to infer overall indicators

2. The following phenomena are positively correlated (ABE)

The more income A family has, the more consumption expenditure it will have

The output of product B increases with the improvement of workers' labor productivity.

C circulation expense rate decreases as product sales increase

D The labor hours required to produce a unit of product decreases with the increase in labor productivity

ETotal production costs increase as product output increases

3． In a range sequence, the group median (ABE)

AThe midpoint value between the upper and lower limits

B is used to represent the average level of each group of sign values.

C cannot be determined in open grouping

D is the group mean

E In open grouping, it can be determined by referring to the group distance of adjacent groups.

4. The principle of compiling the comprehensive index is (AD)

A quality indicator index uses the quantitative indicators of the reporting period as the same measurement factor

B quality indicator index uses the quantitative indicator in the base period as the same measurement factor

C quantity indicator index uses the quantity indicator in the base period as the same measurement factor

D quantitative indicator index uses the quality indicator of the base period as the same measurement factor

3. Judgment questions

1. In various dynamic series, the size of the indicator value is restricted by the length of the period reflected by the indicator. ( × )

2. The research object of socioeconomic statistics is all aspects of the overall socioeconomic phenomenon (×)

3． In sampling inference, the full index value is determined and unique, while the sample index value is a random variable. (√)

4. Compared with a census, a sample survey has a smaller scope, is easier to organize, saves time and effort, and therefore can have more survey items. (√)

5. An investigation was conducted into the living conditions of laid-off workers in a certain city, and the investigation results were required to be reported within one month. The one month period specified is the investigation time. ( × )

Four. short answer questions

1. What is the difference between a quality mark and a quantity mark?

2. What are the different characteristics of period series and time point series?

five. Calculation problems

1. The number of parts (pieces) processed per day by 40 workers in a production workshop is as follows:

30 26 42 41 36 44 40 37 43 35 37 25 45 29 43 31 36 49 34 47 33 43

38 42 32 25 30 46 29 34 38 46 43 39 35 40 48 33 27 28

Requirements: (1) Divide the above data into the following groups: 25-30, 30-35, 35-40, 40-45, 45-50, calculate the frequency and frequency of each group, and prepare a frequency distribution table;

(2) Calculate the average number of parts processed by workers per day based on the finishing table.

Solution: Same as the July 2008 "Principles of Statistics" test questions 5.1.

2. There are 2,000 workers in a factory. A simple repeated sampling method is used to select 100 people as a sample. The average output is calculated to be 560 pieces and the standard deviation is 32.45 pieces. Require:

(1) Calculate the average sampling error;

(2) Estimate the average output and total output range of workers in the factory with a reliability level of 95.45% (Z=2).

untie:

3． In order to study the relationship between product sales and sales profits, a company conducted a survey among its seven companies. It was assumed that product sales were (10,000 yuan) and sales profits were (10,000 yuan). After organizing and calculating the survey data, the results are as follows:

Requirements: (1) Calculate the correlation coefficient between sales and sales profits;

(2) Match the linear regression equation of sales profit to sales.

Solution: (1) Calculate the correlation coefficient between sales and sales profit

(2) Linear regression equation of sales profit on sales

There is an error in the data in this question because the value of the correlation coefficient is between -1 and +1. However, you must at least know the formula and method.

Central Radio and Television University July 2007 "Statistics Principles A" test questions

Multiple choice questions

1. Which of the following groups is grouped by quality mark (C)

A. Enterprises are grouped according to annual production capacity. B. Enterprise workers are grouped according to daily output.

C. Population is grouped by gender D. Families are grouped by annual income level

2. The time for submission of the 2006 annual report on production and operation results of a certain city's industrial enterprises is set on January 31, 2007, so the investigation period is (B).

A. One day B, one month C, one year D, one year and one month

3． The difference between simple grouping and compound grouping is (B)

A. The nature of the selected grouping marks is different. B. The selected grouping marks are somewhat different.

C. The number of groups is different. D. The distance between groups is different.

4. The indicator that directly reflects the overall size is (A).

A. Total index B. Relative index C. Average index D. Variation index

5. The index that reflects the average degree of error between the sample index and the overall index is (C).

A. Mean dispersion B. Probability C. Sampling average error D. Sampling limit error

6. If the correlation coefficient between variable X and variable Y is 1, it means that there is a relationship between the two variables (C)

A. Weak correlation B. Significant correlation C. Complete correlation D. No relationship

2. Multiple choice questions

1. In the Industrial Census, (BCE)

A. The total number of industrial enterprises is the statistical population. B. Each enterprise is the overall unit.

C. Total fixed assets is a statistical indicator D. The number of enterprise equipment is a continuous variable

E. The number of employees in an enterprise is a discrete variable

2. The following are the economic development indicators of a certain region, among which the relative indicators are:

( AVOID ).

A. The sex ratio of men to women in the population is 1.03:1 B. The birth rate is 14.3%

C. The average grain yield per mu is 500 kilograms

D. The completion level of the industrial output value plan is 113%

E. Per capita GDP is 4,500 yuan

3． The factors that affect the size of sampling error are (ABCD).

A. Organizational form of sampling survey B. Method of selecting sample units

C. The degree of variation of the overall studied marker D. The number of sample units drawn

E. Attributes of the overall studied mark

4. The following are quantitative index indices (BC).

A. Labor productivity index B. Total output index

C. Total sales index D. Total price index E. Unit cost index

3. Judgment questions

1. The survey unit of my country's census is "person" and the reporting unit is "household". (√)

2. The key to statistical grouping is to determine group limits and group distances. (× )

3． The larger the value of the signature variation index, the less representative the average index is. (√ )

4. The average index is an important form of the total index and has its own independent application significance. (√)

5. The level of development is the value of each specific indicator in the dynamic sequence, and its expression can only be an absolute number. ( × )

Four. short answer questions

1. Give an example to illustrate how to understand the relationship between the survey unit and the reporting unit.

2. Briefly describe the types and application conditions of variable grouping.

five. Calculation problems

1. The number of parts (pieces) processed per day by 30 workers in a production workshop is as follows:

30 26 42 41 36 44 40 37 37 25 45 29 43 31 36 36 49 34 47 33 43 38 42 32 34 38 46 43 39 35

Requirements: (1) Divide the above data into the following groups: 25-30, 30-35, 35-40, 40-45, 45-50, calculate the frequency and frequency of each group, and prepare a frequency distribution table;

(2) Calculate the average number of parts processed by workers per day based on the finishing table.

Solution: Same as the July 2008 "Principles of Statistics" test questions 5.1.

2. A simple repeated sampling method was used to select 200 parts from a batch of parts for inspection, of which 188 were qualified. Require:

(1) Calculate the sampling average error of the qualification rate of this batch of parts;

(2) Make an interval estimate of the pass rate of this batch of parts based on a reliability level of 95.45% (t=2, which is our current Z).

untie:

Pass rate

Sampling average error of pass rate

(2) Make an interval estimate of the qualification rate of this batch of parts based on a reliability level of 95.45%

The qualification rate range of this batch of parts is:

3． The grain output of a certain region over the years is as follows:

years

2002

2003

2004

2005

2006

Grain production (10,000 kilograms)

434

472

516

584

618

Require:

(1) Calculate the chain development speed and average annual growth in each year.

(2) If grain production in the region develops at a growth rate of 10% from 2006, what level is expected to be achieved in the region by 2010?

Solution: (1) The chain development speed of each year

Average annual growth =

(2) If grain production in the region develops at a growth rate of 10% from 2006

It is expected that by 2010 the region's grain production will reach

Attachment: Commonly used formulas

Structural relative index =

Proportional relative indicator =

Compare relative indicators =

Strength Relative Index =

Relative indicator of plan completion level =

= ，，

Average growth ==

Medical Statistics Review Questions

1. Explanation of terms

1. Overall

2. Sample

3. Random sampling

4. Mutation

5. Probability

6. Random error (accidental error)

7. Parameters

8. Statistics

9. Arithmetic mean

10, median number

11. Percentile

12. Frequency distribution table

13. Geometric mean

14. Interquartile range

15. Variance

16. Standard deviation

17. Coefficient of variation

18. Standard normal distribution

19. Medical reference value range

20. Confidence interval

21. Statistical inference

22. Parameter estimation

23. Standard error and

24. Inspection level

25. Test effectiveness

26. Rate

27. Linear correlation

28. Linear regression

29. Experimental research

30. Regression coefficient

2. Single choice

1. The observation unit is ( ) under study.

A. Sample B. All subjects C. Influencing factors D. Individual E. Observation indicators

2. The whole is composed of ( ).

A. Some individuals B. All objects C. All individuals D. All observations of homogeneous individuals E. The same observation indicators

3. The purpose of sampling is ( ).

A. Study sample statistics B. Infer population parameters from sample statistics

C. Study typical cases D. Study overall statistics

E. Study the characteristics of special individuals

4. Parameter refers to ().

A. Number of participating individuals B. Total number of research subjects in the population C. Statistical indicators of the sample

D. Sum of samples E. Overall statistical indicators

5. Regarding random sampling, which of the following statements is correct ( ).

A. Sampling should be done so that every individual in the population has an equal chance of being selected.

B. Researchers should carefully select individuals when sampling so that the sample can be more representative of the population.

C. Random sampling means randomly selecting individuals

D. To ensure that the sample is more representative, the sample size should be as large as possible

E. Select samples that meet the researcher’s wishes

6. The index that reflects the average of measurement data is ( ).

A. Frequency B. Parameter C. Percentile D. Average E. Statistics

7. The symbol representing the population mean is ( ).

A.σ B.μ C.X D. S E. M

8. Among the following indicators, which one is not a central tendency indicator ( ).

A. Mean B. Median C. Percentile D. Geometric mean E. Mode

9. For data distributed in ( ), the mean is equal to the median.

A. Symmetric distribution B. Positive skew distribution C. Negative skew distribution D. Lognormal distribution E. Normal distribution

10. The incubation periods (days) of a group of patients with a certain disease are: 2, 5, 4, 6, 9, 7, 10 and 18. The average

The indicator should be selected ( ).

A. Median B. Arithmetic mean C. Geometric mean D. Mean E. There is definite data at the end of the percentile

11. When using the frequency distribution table and formula to calculate the median, ( ) is required.

A. The data is symmetrically distributed B. There is definite data at the end of the distribution C. i is the group distance of the group where the median is located

D. The data is normally distributed E. The distance between each group is equal

12. For some patients with chronic diseases, mainly the elderly, the age distribution is concentrated on the older side, which is called ( ).

A. Positive skew distribution B. Negative skew distribution C. Lognormal distribution D. Normal distribution E. Symmetric distribution

13. When compiling frequency distribution, the group distance is usually ( ).

A. Extremely poor 1/20 B. Extremely poor 1/10 C. Extremely poor 1/5 D. Extremely poor 1/4 E. Extremely poor 1/2

14. The following indicators suitable for describing the dispersion trend of measurement data are ( ).

A. Mean, standard deviation, variance B. Range, standard deviation, median C. Mean, median, coefficient of variation

D. Standard deviation, interquartile range, coefficient of variation E. Geometric mean, standard deviation, coefficient of variation

15. Among the following indicators, the indicator that is suitable for describing the discrete trend of skewed distribution is ().

A.Mean deviation B.Interquartile range C.Standard deviation D.Variance E.Coefficient of variation

16. Which of the following statements about standard deviation is incorrect ( ).

A. The standard deviation must be greater than 0

B. Standard deviation and observation indicators have the same measurement unit

C. The standard deviation of the same data must be less than the mean

D. Standard deviation is often used to describe the degree of variation of normally distributed data.

E. Variance and standard deviation are similar indicators that describe the degree of variation.

17. The value of the coefficient of variation ( ).

A. Must be greater than 1 B. Must be less than 1 C. Can be greater than 1, can be less than 1

D. Must be smaller than the standard deviation E. Must be smaller than the mean

18. The observation indicators are two sets of data of height and weight respectively. If you want to compare the degree of variation, you should use ( ).

A.Mean deviation B.Interquartile range C.Standard deviation D.Variance E.Coefficient of variation

19. The normal distribution has two parameters ( ).

A. and S B. μ and σ C. and σ D. μ and S E. μ and CV

20. Among the parameters of the normal distribution, ( ), the “short and fat” the normal curve shape is.

A. The bigger μ is B. The smaller μ is C. The bigger σ is D. The smaller σ is E. σ2 remains unchanged

21. Which of the following statements about standard normal is incorrect ( ).

A. Any data can be transformed into a standard normal distribution through transformation

B. For the standard distribution, P(u≥1.96)=0.975

C. The variance of the standard normal distribution is equal to the standard deviation

D. The curve of the standard normal distribution is unique

E. The standard normal distribution is a symmetric distribution

22. The meaning of standard error is ( ).

A. Reflects the degree of individual variation B. Reflects the location of central tendency C. Reflects the distribution characteristics of the indicator

D. Reflect the difference between the sample mean and the population mean E. Reflect the frequency distribution pattern

23. The reason for sampling error is ( ).

A. The observation object is impure B. The data is not normally distributed C. Individual differences

D. Not categorical variable data E. Random method error

24. Statistical inference includes ( ).

A. Conduct random sampling B. Calculate the standard error of the mean C. Calculate indicators that reflect the average level and degree of variation

D. Make statistical tables and charts E. Carry out parameter estimation and hypothesis testing

25. The purpose of pairing design is ( ).

A. To improve the comparability between groups B. To facilitate the operation C. To use the t test

D. Improve measurement accuracy E. Simple calculation

26. Regarding hypothesis testing, which of the following statements is correct ( ).

A. One-sided testing is better than two-sided testing

B. Whether to use paired t-test or grouped t-test is determined by the experimental design method

C. If the P value is greater than 0.05, the possibility of accepting HO to make a mistake is very small.

D. If the P value is less than 0.05, it is more likely to make an error by accepting H1

E. When using the u test to compare the population means of two samples, there is no requirement for the sample size.

27. When comparing two samples, use the following test levels to determine which level has the smallest type II error ( ).

A.α=0.05 B.α=0.01 C.α=0.10 D.α=0.20 E.α=0.15

28. Both t test and analysis of variance can be used to compare two means. Which of the following statements is correct ( ).

A.t test and analysis of variance can replace each other B.t test can replace analysis of variance

C. Analysis of variance can replace the t test D. The t test and analysis of variance cannot replace each other E. Not necessarily

29. Normality test, according to α=0.10 level, it is considered that the entire population obeys the normal distribution. If the inference is wrong at this time, the probability of error is ().

A. Greater than 0.10 B. Less than 0.10 C. Equal to 0.10 D.β, and β is unknown E.1-β, and β is unknown

30. Comparison of the means of two samples, P<0.01 can be regarded as the mean of the two populations ( ).

A. There is a difference B. The difference is very big C. No difference D. The difference is large E. The difference has practical significance

31. To compare the means of two samples, ( ) cannot be used.

A. Analysis of variance B. t test C. x2 test D. Analysis of variance or t test E. u test

32. Completely randomized design analysis of variance ( ).

A. The SS between groups will not be smaller than the SS within the group B. The SS within the group will not be smaller than the SS between the groups

C. The MS between groups will not be smaller than the MS within the group D. The F value cannot be a negative number E. The F value may be a negative number

33. In analysis of variance, when P<0.05, further ( ) test can be performed.

A.t test B.u test C.t′ test D.F test E.q test

34.In the q test, the relationship between q value and p value is ( ).

A. The larger the q value is, the larger the p value is. B. The smaller the q value is, the smaller the p value is. C. The larger the q value is, the smaller the p value is.

D. The q value has nothing to do with the p value E. None of the above is correct

35. The application conditions of variance analysis are ( ).

A. Randomness B. Normality C. Homogeneity of variances D. A+B+C E. None of the above are correct

36. In the analysis of variance, if P≤α, the conclusion is ().

A. All population means are equal B. At least two population means are unequal

C. At least two samples have different means. D. The means of each sample are not equal. E. The means of each population are not equal.

37. The number of people with hepatitis in a certain place in a certain year accounts for 10.1% of the number of infectious diseases in the same year. This indicator is ( ).

A. Rate B. Composition ratio C. Incidence rate D. Central tendency E. Time point prevalence

38. Men are known to be infected with hookworm at a higher rate than women. To compare the overall hookworm infection rate of residents in two places, but the gender composition of the two places is different, the appropriate comparison method is ().

A. Comparison by gender B. x2 test for comparison of two rates C. Not comparable and cannot be compared

D. Standardize gender and then compare E. Make a hypothesis test of the difference between the two rates

39. When using relative numbers, the common mistake is ( ).

A. Treat the composition ratio as a rate B. Treat the composition ratio as a relative ratio C. Treat the relative ratio as a rate

D. Treat the rate as a composition ratio E. Treat the standardized rate as a composition ratio

40. To compare the prevalence of a certain occupational disease among workers of a certain type of work in two factories, A and B, the principle of standardization is ( ).

A. Assume that the number of workers in two factories A and B is the same

B. Assume that the number of workers suffering from a certain occupational disease in two factories is the same

C. Assume that the seniority composition ratio of workers in a certain type of work in factories A and B is the same

D. Assume that the prevalence of an occupational disease in factories A and B is the same

E. Assume that the number of workers in factories A and B is the same.

41. To compare the prevalence of a certain occupational disease among workers of a certain type of work in two factories, A and B, and standardize the length of service, the conditions for the standard composition are ().

A. The age composition of workers in Factory A. B. The age composition of workers in Factory B. C. The age composition of workers in the merger of Factory A and Factory B.

D. The age composition of the relatively stable local population E. The length of service composition of the merged workers of factories A and B

42. Sample rate p and population rate π. The condition for comparison using u test is ( ).

A. The sample size n is large, np and n(1-p) are both greater than 5. B. The sample size n is large, and the overall rate is π. close to 1

C. The sample size n is large, and the sample rate p is close to 0.5. D. The sample size n is large, and the sample rate p is close to 1.

E. The sample rate p is not too small

43. From two articles A and B, we found four-square table data comparing two rates in similar studies. After x2 test, article A x2>x20.01(1), article B x2>x20.05(1), both articles It is concluded that the difference between the two rates is significant, which can be considered as ( ).

A. The results of the two papers are contradictory. B. The results of the two papers are basically consistent. C. The results of the first paper are more credible.

D. The results of Article A are not credible E. Article A shows that the overall difference is large

44. Comparing the four sample rates x2>x20.01(3), it can be considered as ( ).

A. The population rates are not equal or not completely equal. B. The population rates are not equal. C. The sample rates are not equal.

D. The sample rates are not equal or not equal. E. The two population rates are equal.

45. Degrees of freedom of four-grid table ( ).

A. Not necessarily equal to 1 B. Must be equal to 1 C. Equal to the number of rows × the number of columns D. The sample size is reduced by 1 E. None of the above is correct

46. The shape of x2 distribution ( ).

A. Same as normal distribution B. Same as t distribution C. Symmetrical distribution D. Related to the degree of freedom υ E. Related to the sample size n

47. When the total of the periphery of the four-cell table remains unchanged, if the actual frequency of a certain cell changes, then its theoretical frequency ( ).

A. Increase B. Decrease C. No change D. Uncertain E. Increase or decrease with the increase or decrease of the actual frequency of the grid

48. The degrees of freedom of the R×C table x2 test are ( ).

A.R-1 B.C-1 C. R×C-1 D.(R-1)(C-1) E.R×C-2

49. To compare the case fatality rates of three infectious diseases, diphtheria, Japanese encephalitis and dysentery, in a certain place in 1956, the statistical chart that should be chosen is ( ).

A. Line graph B. Semi-logarithmic line graph C. Histogram D. Bar graph E. Percent bar graph

50. The requirements for titles of statistical charts and tables are ( ).

Both titles are at the top

B. Both titles are below

C. The title of the statistical table is at the bottom and the title of the statistical chart is at the top.

D. The title of the statistical table is at the top, and the title of the statistical chart is at the bottom.

E. The position can be set at will by the researcher

3. True or False Questions

1. A hospital admitted 10 patients with a certain lung disease, and 8 of them smoked, accounting for 80%. The conclusion is that "smoking is the cause of the disease."

2. The prevalence rates of a certain disease in a chemical plant for four consecutive years are 6.0%, 9.7%, 11.0%, and 15.4% respectively. Then the total prevalence rate of the disease is (6.0+9.7+11.0+15.4)/4=10.53 %.

3. The crude mortality rate of malignant tumors in County A is higher than that in County B. It can be considered that the level of prevention and control in County A is worse than that in County B.

4. During summer military training in a certain university, 21 cases of heat stroke occurred, among which students from the north were 2.5 times more likely to suffer from heat stroke than students from the south. The conclusion was that "students from the north are prone to heat stroke."

5. The researchers measured the number of red blood cells in the peripheral blood of 100 patients, and the data obtained were count data.

6. Statistical analysis includes statistical description and statistical inference.

7. Measurement data, counting data and grade data can be converted into each other according to analysis needs.

8. When preparing a frequency distribution table, the more groups the better.

9. The group distances in the frequency distribution table must be equal.

10. The mean represents the average level of a set of homogeneous measurement data, and different means can be compared with each other.

11. For samples

12. The geometric mean is suitable for describing the central tendency of multiple relationship data.

13. Hypothesis testing must be performed when comparing the means of two random samples.

14. Standard deviation and standard error are both indicators that reflect the degree of variation.

15. If the difference between the means of two samples is statistically significant after testing, it means that the means of the two samples are different.

16. In analysis of variance, if the treatment factor has no effect, the F value must be equal to 1.

17. Completely randomized design data can be statistically processed using random block design variance analysis to improve statistical efficiency.

18. In the analysis of variance, the SS between groups must be greater than the SS within the group.

19. In experimental design, the larger the sample content, the more consistent it is with the principle of repetition and the greater the experimental error can be reduced.

20. Randomly select 1,000 2-year-old children for immunization against a certain disease. After 8 years, 80% of the vaccinators do not suffer from the disease, and the vaccine is considered to have a high protection rate.

4. Short answer questions

1. There are 50 students in Class A and Class B of a certain grade. Select 10 people from each class to measure their height and find their average height. If the average height of Class A is greater than that of Class B, can it be inferred that the average height of all students in Class A is greater than that of Class B? Why?

2. Statistical analysis requires which four characteristics each sample should have.

3. Briefly describe the preparation method and main uses of frequency distribution tables.

4. What are the main statistical indicators that reflect central tendency? What are the similarities and differences in their scope of application?

5. The blood and urine nitrogen contents (mmol/L) of 10 breast cancer patients after chemotherapy were measured to be 3.43, 2.96, 4.43, 3.03, 4.53, 5.25, 5.64, 3.82, 4.28, 5.25 respectively. Question: (1) What is this data? Overall data or sample data? (2) What is its overall homogeneous basis? (3) To express the average level of data, what statistical index should be used?

6. Try to compare the advantages of standard deviation and variation systems in describing the degree of variation in data.

7. Briefly describe the meaning of medical reference value range.

8. Briefly describe the differences and connections between the standard normal distribution and the normal distribution.

9. It is known that the average serum total cholesterol of 40-year-old normal women in a certain place is 4.46mmol/L, and the standard deviation is 1.02mmol/L. A medical institution randomly selected 25 normal adult women from the area and measured their average serum total cholesterol to be 4.77mmol/L. Try to point out the reason why 4.77mmol/L is different from 4.65mmol/L, and choose the correct indicator to express its size. .

10. What are the characteristics of the sampling distribution of the sample mean?

11. In the hypothesis test of comparing the means of two samples, what is the difference in meaning between the two cases of 0.02<P<0.05 and 0.001<P<0.002?

12. During hypothesis testing, H0 is rejected when P≤α. What is the theoretical basis?

13. How to reasonably set the inspection level α?

14. Take t test as an example to explain the difference between test levels α and P.

15.What are the situations of matching data? Please give examples.

16.What are the data requirements for analysis of variance?

17. What are the application conditions of the four-square table x2 test?

18.What are the commonly used relative indicators? Please explain the meaning, calculation methods and characteristics of various relative numbers?

19. What issues should we pay attention to when using relative numbers? ,

20.What problems is the x2 test used to solve?

5. Calculation questions

1. It is known that the incubation periods of 10 cases of a certain infectious disease are 5, 6, 8, 3, 2, 4, 6, 10, 9, >14 days. Please calculate its discrete trend indicator?

The incubation period of infectious diseases is generally not normally distributed, and the incubation period of one patient is open data, so the interquartile range is used to describe the degree of variation.

2. In the quality of life assessment, a normal person received the following score on the 130-person scale (out of 100 points)

A quality of life rating scale score

scale score

20~

40~

60~

80~100

reciprocal

Question: What indicator should be used to describe the dispersion trend of this data?

3. In 1979, a city surveyed the pulse rate (beats/min) of 160 20-year-old male students. The known data obeyed a normal distribution, and the mean was 76.1 and the standard deviation was 9.32. It is estimated that the pulse rate of 20-year-old male students in this city 95% confidence interval for pulse number?

4. The serum cholesterol of 500 coronary heart disease patients aged 40 to 50 years was randomly checked in a certain place. The mean was 228.6 mg/dL and the standard deviation was 46.8 mg/dL. At the same time, the serum cholesterol of 30 coronary heart disease patients over 60 years old was randomly checked. For serum cholesterol, the mean was 230.8mg/dL and the standard deviation was 54.9mg/l. Try to calculate the 99% confidence interval of serum cholesterol in patients with coronary heart disease in different age groups.

5. In a city in 1982, the average height of 120 12-year-old boys was measured to be 143.10cm, with a standard deviation of 5.67cm. At the same time, the average height of 120 12-year-old girls was measured to be 141.60cm, with a standard deviation of 10.88cm. Try to estimate the overall mean of the height of 12-year-old boys and girls to compare which estimate is better (α=0.05)

6. Through previous large-scale surveys, it is known that the birth weight of babies in a certain place is 3.30kg. Today, the average birth weight of 35 dystocia babies was measured to be 3.42kg, with a standard deviation of 0.40kg. Is the birth weight of dystocia babies in this place different from that of ordinary babies?

7. There are currently 900 staff in a hospital, including 760 males and 140 females. During a flu outbreak, 108 people fell ill, including 79 males and 29 females. Try to calculate: (1) the total incidence of influenza in the hospital; (2) the incidence of influenza in males and females; (3) the percentage of male and female patients in the total number of patients.

8. Through a large number of repeated investigations, it is known that the fever response rate of a certain vaccine is 20%. However, after 100 people in a certain place used another batch of the vaccine, the fever was measured in 14 people. I asked whether the fever response rate of this batch of vaccine is the same as that of 100 people in a certain place. The original investigation was different?

9. Among 80 boys in a mountainous primary school, 23 were infected with paragonimiasis, an infection rate of 28.75%; 13 of 85 girls were infected, with an infection rate of 15.29%. Is there any difference in the paragonimiasis infection rates among male and female students?

The third set of test papers and reference answers

1. Multiple choice questions 20 points

1. The serum titers of 7 people are 1:2, 1:4, 1:8, 1:16, 1:32, 1:64, 1:128, then the average titer is __C__

A．1:12.4 B．1:8 C．1:16 D．1:8~1:16

2. To compare the variation in height and weight between two sets of data, ___A___ should be used

A. Coefficient of variation B. VarianceC. Extremely poor D. standard deviation

3． Which of the following statements about individual variation is incorrect is __C__

A. Individual variation is inherent in an organism. B. Individual variation is regular.

C. Increasing the sample size can reduce individual variation.

D． The distribution type of indicators reflects the distribution pattern of individuals.

4. The principle of experimental design is __C___

A. Control, random, balanced B. Random, repetitive, balanced

C. Control, repetition, random D. Random, repeated, identical

5. The indicator indicating the intensity of a certain phenomenon is __B____

A. average b. rate c. Composition ratio D. compare to

6. To study whether the prevalence of diabetes is different among people with four different blood types, use the chi-square test for multiple rate comparisons. After constructing an R*C table with 4 rows and 2 columns, the degree of freedom of the chi-square value is __C_

A. 8 b. 1C. 3D. Depends on sample content

7. Type I errors in hypothesis testing are those made by _A__.

A. Rejected H0 B. Do not reject H0 that actually holds

C. Rejected H0 D. which was actually untenable. Do not reject H0 which is not actually true

8. When the sample size is fixed, which of the following inspection levels is chosen to obtain the highest inspection efficiency (1-β)__D___

A． B． C． D．

9. The data requirement for the t test of two sample means is _D___

A. Normality, independence, homogeneity of variances B. The data is representative

C. For quantitative data D. All of the above are true

10. Chi-square test for comparison of four rates, if the P value is less than 0.01, the conclusion is _D__

A. The four overall rates are not equal; B. The four sample rates are not equal;

C. The four overall rates are certainly not equal or not entirely equal; D. The four overall rates are not equal or not entirely equal.

2. Explanation of terms 10 points

baby boy x1

7.3

7.9

8.0

9.3

7.8

6.5

7.6

6.6

8.4

6.7

7.5

baby girl x2

7.1

7.9

6.4

6.6

8.0

6.0

7.2

6.8

7.8

5.3

6.6

7.3

1. Correlation coefficient; 2. Sampling error; 3. Coefficient of variation; 4. Overall parameters; 5. Rate;

Answer: See the corresponding place in the book

3. Fill in the blanks 10 points

1. The four commonly used probability sampling methods are: simple random sampling, mechanical sampling (systematic sampling), stratified sampling, and cluster sampling.

2. The content of statistical inference mainly includes parameter estimation and hypothesis testing.

3. Clinical observation of 7 patients with a certain disease, their incubation periods (days) are: 3, 7, 9, 5, 6, 9, 16, then the total period is 13 days.

4. 20 observation subjects were subcutaneously injected with a certain vaccine, and the antibody titer was measured after a period of time. The results were: ⑴ effective ⑵ invalid ⑶ effective (4) effective... ⒇ invalid, what type of data does this data belong to? Data counting data .

5. The basic elements of experimental research are: processing factors, subjects, and experimental effects.

4. Short answer questions 20 points

1. In the rank sum test, why should the "average rank" be given to the same data between different groups, but the same data in the same group do not need to calculate the average rank?

Answer: Ranking in this way does not affect the calculation of the rank sum of the two groups, or does not cause bias in the calculation of the rank sum of the two groups.

2 A doctor used a certain drug to treat 10 cases of bronchial asthma in children, and 8 were cured. He concluded that "the cure rate of this drug for bronchial asthma in children is 80%, and it is worthy of promotion."

Answer: First, there is no control group, and second, the number of samples is too small, resulting in large sampling errors and wide confidence intervals.

3． The 95% confidence interval of the average hemoglobin of 1-year-old infants in a certain place is 116.2~130.1 (g/L). What does it mean? The reference value range of 95% of the hemoglobin of normal 1-year-old babies in this place is 111.2~135.1 (g/L). What does it mean?

Answer: It means that the overall average hemoglobin of 1-year-old infants in this area is 116.2~130.1 (g/L), and the estimated probability of being correct is 95%

It means that 95% of normal 1-year-old babies in this area have hemoglobin values between 111.2 and 135.1 (g/L)

4. For the same set of data, if the r calculated by correlation analysis is larger, the b calculated by regression analysis will also be larger. Why?

Answer: There is no such rule. The size of the r value in correlation analysis only indicates the close connection between variables, while the size of b in regression analysis indicates the quantitative relationship between the two.

5. Analysis and calculation questions 40 points

1. To examine whether male infants are heavier than female infants at birth, researchers randomly selected the birth data of 12 Caucasian male infants and 12 Caucasian female infants from the Child Health and Development Research Center at the University of California, Berkeley (Unit: pound).

(1) Is the data numerical variable data or categorical data? Numeric variable data

(2) To compare whether the birth weights of Caucasian males and females are different, should a grouped t test or a paired t test be used? Grouped t-test

(3) After calculation, the t value is 2.16. It is known that when the degree of freedom is 22, the t boundary value corresponding to the bilateral area of 0.05 is 2.07. When the degree of freedom is 11, the t boundary value corresponding to the bilateral area of 0.05 is 2.20. Try to write down the entire process of hypothesis testing and draw conclusions.

Answer: H0: The birth weight of Caucasian male infants and female infants is the same, that is, μ1 = μ2

H1: μ1≠μ2 α=0.05

t=2.16 ν=22 t>t0.05/2,22=2.07 p<0.05

Rejecting H0 at the α=0.05 level, it is believed that the birth weight of Caucasian male infants and female infants is different, and male infants are heavier than female infants.

2. A hospital uses two treatments, A and B, to treat simple indigestion. The results are in the table below.

therapy

Number of people treated

Number of people cured

Number of people who have not recovered

Cure rate (%)

First

78.79

Second

94.74

total

87.32

(1) Please calculate the minimum theoretical number. Tmin=9*33/71=4.18

(2) If we want to compare whether the cure rates of the two treatments are equal, what testing method should be used? Four-grid table corrected chi-square test

(3) The known test statistic is 2.92, please draw a conclusion.

Because χ2=2.92<3.84, P>0.05

Conclusion: Accepting the test hypothesis at the α=0.05 level, it can be considered that the difference in cure rates between the two treatment methods is not statistically significant.

3 Compare the survival time of cats and rabbits under hypoxic conditions (time: minutes)

Cat

rabbit

survival time

Rank

survival time

Rank

5.5

(1) What experimental design method does this data belong to? Comparison of two sample data in completely randomized design

(2) Rank the data; see table

(3) What is the total rank sum of this data? What is the actual rank sum of each group?

Total rank sum: 120, cat group: 80.5, rabbit group 39.5

(4) Write the hypothesis for hypothesis testing on the data.

H0: The overall distribution of survival time in the two groups is the same.

4. Please complete the following blanks and conduct a descriptive analysis.

age)

population number

total number of deaths

malignant tumor deaths

Deaths from malignant tumors account for % of total deaths

Malignant tumor mortality rate (1/100,000)

Age-specific mortality rate (‰)

82920

( )

2.90

( )

20-

( )

19.05

25.73

( )

40-

28161

172

( )

60-

( )

total

167090

715

12.59

( )

Summary of health statistics test questions

Guess you like