Power analyses for longitudinal trials and other clustered designs

Authors

  • X. M. Tu,

    Corresponding author
    1. Department of Biostatistics and Computational Biology, University of Rochester, 601 Elmwood Avenue, Rochester, NY 14642, U.S.A.
    2. Department of Psychiatry, University of Rochester, 601 Elmwood Avenue, Rochester, NY 14642, U.S.A.
    • Department of Biostatistics and Computational Biology, University of Rochester, 601 Elmwood Avenue, Box 630, Rochester, NY 14642, U.S.A.
    Search for more papers by this author
    • Professor.

  • J. Kowalski,

    1. Department of Oncology and Biostatistics, Johns Hopkins University, U.S.A.
    Search for more papers by this author
    • Assistant Professor.

  • J. Zhang,

    1. Department of Biostatistics and Epidemiology, University of Pennsylvania School of Medicine, U.S.A.
    Search for more papers by this author
    • Graduate Student.

  • K. G. Lynch,

    1. Department of Biostatistics and Epidemiology, University of Pennsylvania School of Medicine, U.S.A.
    Search for more papers by this author
    • Assistant Professor.

  • P. Crits-Christoph

    1. Department of Psychiatry, University of Pennsylvania School of Medicine, U.S.A.
    Search for more papers by this author
    • Professor.


Abstract

Existing methods for power and sample size estimation for longitudinal and other clustered study designs have limited applications. In this paper, we review and extend existing approaches to improve these limitations. In particular, we focus on power analysis for the two most popular approaches for clustered data analysis, the generalized estimating equations and the linear mixed-effects models. By basing the derivation of the power function on the asymptotic distribution of the model estimates, the proposed approach provides estimates of power that are consistent with the methods of inference for data analysis. The proposed methodology is illustrated with numerous examples that are motivated by real study designs. Copyright © 2004 John Wiley & Sons, Ltd.

Ancillary