ABSTRACT
Formulas for sample size calculation for testing goodness-of-fit and independence (or association) under an r * c contingency table are derived based on various chi-square type test statistics such as Pearson's chi-square and likelihood ratio test statistics. Procedures for sample size calculation for testing categorical shift using McNemar's test and/or Stuart-Maxwell test are derived. Further research in sample size estimation based on a fixed alternative is needed. Sample size calculation formulas for testing independence (or association) with single stratum and multiple strata are introduced based on various chi-square test statistics. When the data are binary, the Cochran-Mantel-Haenszel (CMH) test is probably the most commonly used test procedure, and can adjust for differences among centers. The chapter considers testing for carryover effect in a 2 * 2 crossover design and presents some practical issues. Pearson's test is commonly used in the situation where the marginal distribution of the numbers of the subjects for each treatment is unknown.
