First, the step of hypothesis testing
Specific code can be checked; figuring out scenarios and understand the implementation of the principle of
1. Set the null and alternative hypothesis
2. Set the significance level a = 0.05
3. Select the way of hypothesis testing
Determine the type of test
(1) Single samples were tested: a sample
(2) Related detector pairs: two cases tested the same group of people, data collection
(3) A / Btest: test by two groups of people, high similarity, to ensure homogeneity;
Analyzing sampling distribution type:
Common hypothesis testing Z-test, t test, chi-square test, F test and the like.
Small sample, less than 30, a large sample is greater than 30
Under the circumstances known variance is averaging Z test.
Averaging is unknown variance t test
Judgment unilateral or bilateral detection detection?
python code will be different
Concluded that judge
2. The law of large numbers and the central limit theorem