Tests for cross-tabulated count data

Navigation:  Resources > Tests Index >

Tests for cross-tabulated count data

Previous pageReturn to chapter overviewNext page

Pearson's Chi-square test - The standard chi-square test is applied to counts of events classified by two or more characteristics arranged as a cross-classification table of r rows and c columns. The test evaluates whether the observed distribution is significantly different from that expected based on probabilities determined from the row and column marginal totals and an assumption that the rows and columns are independent

Fisher's Exact test - This test is typically applied to count data where the cross-tabulation is of dimensions 2x2 and the total sample size is small

G test - This test is almost identical to the chi-square test for contingency tables. The difference is in the way in which the statistic is computed, being based on a maximum likelihood (log likelihood) measure

McNemar's test - This is a simple test of a 2x2 table of paired data with the null hypothesis being that the marginal probabilities are equal