EM-REML estimation of covariance parameters in Gaussian mixed models for longitudinal data analysis

This paper presents procedures for implementing the Eh I algorithm to compu te REML estimates of variance covariance components in Gaussian mixed model s for longitudinal data analysis. The class of models considered includes r andom coefficient factors, stationary time processes and measurement errors . The EM algorithm allows separation of the computations pertaining to para meters involved in the random coefficient factors from those pertaining to the time processes and errors. The procedures are illustrated with Pothoff and Roy's data example on growth measurements taken on 11 girls and 16 buys at four ages, Several variants and extensions are discussed.