HPFMM Procedure
The HPFMM procedure is a highperformance counterpart of the FMM procedure that fits statistical models to data for which the distribution of the response is a finite mixture of univariate
distributionsthat is, each response comes from one of several random univariate distributions that have unknown probabilities. It is a highperformance version of the FMM procedure in SAS/STAT software.
PROC HPFMM runs in either singlemachine mode or distributed mode. The procedure enables you to do the following:
 model the component distributions in addition to the mixing probabilities
 fit finite mixture models by maximum likelihood or Bayesian methods
 fit finite mixtures of regression and generalized linear models
 model overdispersed data
 perform Bayesian analysis
 estimate multimodal or heavytailed densities

 fit zeroinflated or hurdle models to count data with excess zeros
 specify the response variable by using either the response syntax or the events/trials syntax
 specify constraints among the parameters of the mixture model for multithreaded and distributed computing
 performs weighted estimation
 specify performance options for multithreaded and distributed computing

For further details see the SAS/STAT User's Guide:
The HPFMM Procedure
(
PDF  HTML )
Examples