Power and Sample Size for Testing Homogeneity of Relative Risks in Prospective Studies



Summary. Power and sample-size formulas for testing the homogeneity of relative risks using the score method are presented. The homogeneity score test (Gart, 1985, Biometrika72, 673–677) is formally equivalent to the Pearson chi-square test, although they look different. Results of this paper may be useful in assessing the validity of the model of a common relative risk before combining several 2 × 2 tables or in designing a prospective study for detecting heterogeneity of relative risks.