Biometrics 1999; 55:957-964.
Relating the Classical Covariance Adjustment Techniques of Multivariate Growth Curve Models to the Modern Univariate Mixed Effects Models.
Mikulich, S., K., Zerbe G. O., Jones, R. H., Crowley, T. J.
The relationship between the modern univariate mixed model for analyzing longitudinal data, popularized by Laird and Ware, and its predecessor, the classical multivariate growth curve model, summarized by Grizzle and Allen, has never been clearly established. Here, the link between the two methodologies is derived, and balanced polynomial and cosinor examples cited in the literature are analyzed with both approaches. Relating the two models demonstrates that classical covariance adjustment for higher-order terms is analogous to including them as random effects in the mixed model. We apply mixed model techniques to cosinor analyses of a large, unbalanced data set to demonstrate the relevance of classical covariance structures that were previously conceived for use only with completely balanced data.