Multiple imputation and posterior simulation for multivariate missing datain longitudinal studies

This paper outlines a multiple imputation method for handling missing data in designed longitudinal studies. A random coefficients model is developed to accommodate incomplete multivariate continuous longitudinal data. Multiv ariate repeated measures are jointly modeled; specifically, an i.i.d. norma l model is assumed for time-independent variables and a hierarchical random coefficients model is assumed for time-dependent variables in a regression model conditional on the time-independent variables and time, with heterog eneous error variances across variables and time points. Gibbs sampling is used to draw model parameters and for imputations of missing observations. An application to data from a study of startle reactions illustrates the mo del. A simulation study compares the multiple imputation procedure to the w eighting approach of Robins, Rotnitzky, and Zhao (1995, Journal of the Amer ican Statistical Association 90, 106-121) that can be used to address simil ar data structures.