Chi-square test is a widely used hypothesis test method, and its applications in statistical inference of classified data include: chi-square test for comparing two ratios or two constituent ratios; Comparison of multiple ratios or multiple composition ratios and chi-square test of correlation analysis of classified data.
The comparison of two independent samples can be divided into the following three situations:?
1, all theoretical numbers T≥5, total sample size n≥40, Pearson chi-square test. ?
2. If the theoretical number t < 5 but T≥ 1 and n≥40, the chi-square test of continuity correction is used. ?
3. If the theoretical number t < 1 or n < 40 exists, Fisher test is used. ?
The above applies to four-grid tables.
Application conditions of chi-square test of R×C table:?
1 and the number of squares whose theoretical number is less than 5 in the R×C table cannot exceed 1/5.
2. The theoretical number cannot be less than 1. My experiment also doesn't meet the chi-square test of R×C table. This can be achieved by increasing the number of samples and merging columns.