Abstract

The Chi square (?2) test is used to examine whether distributions of categorical variables differ from one another. The Chi Square statistic compares the counts of categorical responses between two (or more) independent groups. Pearson’s chi-square test is most widely used of many chi-square test. A better approximation can be calculated by reducing the absolute value of each difference between observed and expected frequencies by 0.5; which is called Yates’s correction for continuity. Fisher’s exact test is employed when sample size is small in comparisions.

Key words: Chi-square test, expected frequency, observed frequency