SummaryMuch attention has been given to the problem ofpredicting future obeervatiomfor some individual within a random coefficient regreasion (RCR) model, using the previous observations on that individual aa well es the information from the re& of the data material. In thia paper, the literature on this subject ie critically reviewed and new methode of linear prediction are proposed for the g e n d RCR model. Exact reaulte am derived for the mean squared errom of Bome predictors in a spacial case, but this ie not poeaible in the general RCR model when ite parametem are not known. In this model, the old and new predictom are compared in a simulation efudy, and further illustrated by prediction in a medical data material.
SummaryRCR models are reviewed. Various variance estimators are described, among them a new one.Thew variance eathatore are compared in a simulation study. An obahtric data aet is subjected to a detailed analysis by meana of RCR techniques. In particular, interval estimation ia considered.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.