Abstract
SummaryWe obtain closed‐form asymptotic variance formulae for three point estimators of the intraclass correlation coefficient that may be applied to binary outcome data arising in clusters of variable size. Our results include as special cases those that have previously appeared in the literature (Fleiss and Cuzick, 1979,Applied Psychological Measurement3,537–542;Bloch and Kraemer, 1989,Biometrics45,269–287;Altaye, Donner, and Klar, 2001,Biometrics57,584–588). Simulation results indicate that confidence intervals based on the estimator proposed by Fleiss and Cuzick provide coverage levels close to nominal over a wide range of parameter combinations. Two examples are presented.