BAYES LINEAR METHODS FOR GROUPED MULTIVARIATE REPEATED MEASUREMENT STUDIES WITH APPLICATION TO CROSSOVER TRIALS

This paper offers a study in the application of Bayes linear methods. We outline a general approach to the analysis of mean effects for grou ped multivariate repeated measurement studies, based upon partial beli ef specification. We suggest a method for coherent partial prior speci fication for such structures, based on moment evaluations for exchange able data. We describe the general collection of interpretive and diag nostic tools termed 'Bayes linear methods', and suggest a simple crite rion for trial design. The theory is illustrated by analysis of a cros sover trial concerned with side effects of kidney dialysis.