Traj uses a discrete mixture model to model longitudinal data. This model allows for data grouping using different parameter values for each group distribution. Groupings may identify distinct subpopulations. Alternatively, groupings may represent components for approximating an unknown (possibly complex) data distribution.

 

Supported distributions are: censored (or regular) normal, zero inflated (or regular) Poisson, and Bernoulli distributions (logistic model). The censored normal model is useful for psychometric scale data, the zero inflated Poisson model useful for count data with more zeros than would be expected under the Poisson assumption, and the Bernoulli model useful for 0/1 data. The model is appropriate for data with average values changing smoothly as a function of the dependent variable (time, age, ...). Some sharp changes can be handled through the inclusion of time dependent covariates.

linked reference material

A SAS Procedure Based on Mixture Models for Estimating Developmental Trajectories

Advances in Group-Based Trajectory Modeling and a SAS Procedure for Estimating Them