Abstract
This paper is concerned with profilc analysis of growth curves of several groups. Two extended growth curve models introduced by Verbyla and Venables (1988) are considered. The first is a growth curve model with covariates, which has a random-effects covariance structure based on a single response variable; the second is a multivariate growth curve model with parallel profiles, which has a multivariate random-effects covariance structure based on several response variables. Test statistics for testing hypotheses about mean parameters are suggested under the random-effects covariance structures.