Descriptive statistical analysis method is a method of application classification, tabulation, graphical data and indicators to summarize the general distribution of books, and inferential statistical analysis method is through the application of statistical random sampling method, the sample data obtained conclusions to data analysis overall.
Statistics statistical information contained in the sample data needs to be fused and abstract generalization composite indicator to give these indicators reflect the sample data is called data descriptive statistics features fall into two categories represent a class of such center position data, the mean, median, etc. are all discrete degree data indicates a category such as variance, standard deviation, range, etc. are used to measure the degree of off-center around.
For a given class, the number of cases falling within such frequency is referred to, falling within mainly by the frequency distribution table, bar charts, pie charts, and histograms in the class and the ratio of the number of cases integrated number of cases referred to the relative frequency analysis Fig.
In frequency analysis, pie and bar charts are generally applicable to the category with less number of categorical variables, if more number of categories, recommended to choose the histogram.
The central region is a set of data refers to a tendency to move closer to a center value, the center position of the descriptive statistics data distribution is referred to as position statistics for continuous variables and ordinal variable index data described trends are the mean center, median number, mode, five percent at the end homogeneous, for qualitative variables and specification data center trends, only the mode.
Observations in ascending order, and excluding the mean value calculation section across the sorted data sequence obtained is called off end.
The mode is the most frequently observed value of the value appears, this reaction the central tendency of the set of observations.
The mode is qualitative data, the central area is only used temporary, but the mode can be used for system data.
Today's data center trend indicators feeling is not enough to make decisions, for example, if the average family income gap a little country, and the gap between income disparity in another country great, and there are a lot of poor families, there are also a lot of very wealthy families Well, what even middle-income families in both countries exactly the same income, their family income is still different.
Of the observer, the size of which is the case where the degree of dispersion of each observed value deviates from the mean value and the difference between the mean of the observations, the difference may be used to describe the variation of the size of the individual, but it is not representative of the overall degree of dispersion .
To measure the mean standard error of the mean differences between different samples, if the difference between two sample means and standard error ratio is less than - two or more than two, there can be concluded that the two means significant difference, and thus concluded that two samples from two different overall.
When two groups of discrete data size level, if the difference is too familiar with the measurement scale, or the dimension data is not the same, then direct comparison of the two standard deviation is not appropriate, first need to eliminate the influence of the measurement scale of the amount of steel the coefficient of variation can be made for these effects.
spss the number of menus can be descriptive statistical analysis of variance test for independent samples in body analysis factor analysis, and many other custom analysis process spss module can also generate most of the children descriptive statistics.