REML estimation for repeated measures analysis

Authors

C. A. McGilchrist, University of New South Wales
Brian R. Cullis, Agricultural Research InstituteFollow

RIS ID

79124

Publication Details

McGilchrist, C. A. & Cullis, B. R. (1991). REML estimation for repeated measures analysis. Journal of Statistical Computation and Simulation, 38 (1-4), 151-163.

Abstract

Models for repeated measures or growth curves consist of a mean response plus error and the errors are usually correlated. Both maximum likelihood and residual maximum likelihood (REML) estimators of a regression model with dependent errors are derived for cases in which the variance matrix of the error model admits a convenient Cholesky factorisation. This factorisation may be linked to methods for producing recursive estimates of the regression parameters and recursive residuals to provide a convenient computational method. The method is used to develop a general approach to repeated measures analysis.