These models allow for incomplete data across time, time-invariant and time-varying covariates, and can estimate individual change across time. Because substance use outcomes are often measured in terms of dichotomous or ordinal categories, this presentation focuses on categorical versions of RRM. Specifically, it describes an ordinal RRM that includes the possibility that covariate effects vary across the cutpoints of the ordinal outcome. This latter feature is particularly useful because a treatment can have varying effects on full versus partial abstinence. The article uses data from a smoking cessation study to illustrate application of this model for analysis of longitudinal substance use data. The article observes that, since longitudinal designs are increasingly used to study alcohol, smoking, and other substance use patterns across time, it is important that statistical methods are developed and used to extract the most out of the longitudinal datasets. It concludes that the RRM's provide an attractive approach for addressing some key questions. Tables, figure, references