摘要：Pattern-mixture models have gained considerable interest in recent years. Patternmixture modeling allows the analysis of incomplete longitudinal outcomes under a variety of missingness mechanisms. In this manuscript, we describe a SAS program which combines R functionalities to fit pattern-mixture models, considering the cases that missingness mechanisms are at random and not at random. Patterns are defined based on missingness at every time point and parameter estimation is based on a full group-bytime interaction. The program implements a multiple imputation method under so-called identifying restrictions. The code is illustrated using data from a placebo-controlled clinical trial. This manuscript and the program are directed to SAS users with minimal knowledge of the R language.
