DESIGN AND ANALYSIS OF INTRA-SUBJECT VARIABILITY IN CROSS-OVER EXPERIMENTS

Recently, interest has grown in the development of inferential techniq ues to compare treatment variabilities in the setting of a cross-over experiment. In particular, comparison of treatments with respect to in trasubject variability has greater interest than has inter-subject var iability. We begin with a presentation of a general approach for stati stical inference within a cross-over design. We discuss three differen t statistical models where model choice depends on the design and assu mptions about carry-over effects. Each model incorporates t-variate ra ndom subject effects, where t is the number of treatments. We develop maximum likelihood (ML) and restricted maximum likelihood (REML) appro aches to derive parameter estimators and we consider a special case in which closed-form expressions for the variance component estimators a re available. Finally, we illustrate the methodologies with the analys is of data from three examples.