"RRGibbs" - a program for simple random regression analyses via Gibbs sampling.
Karin Meyer · 2002
INTRODUCTION Random regression (RR) models are a popular choice for the analysis of longitudinal data or ’repeated’ records. Programs for estimation of the corresponding covariance functions via restricted maximum likelihood (REML) are available (e.g. Gilmour et al., 1999; Meyer, 1998), but high computational demands of REML analyses severely limit their feasibility. Bayesian analysis using Gibbs sampling provides an alternative which is markedly simpler to implement and requires considerably less memory than REML, thus facilitating large scale analyses.