The MCMC Procedure

 

Syntax: MCMC Procedure

The following statements are available in PROC MCMC. Items within < > are optional.

PROC MCMC <options> ;
ARRAY arrayname <{ dimensions }> ;
BEGINCNST/ENDCNST ;
BEGINNODATA/ENDNODATA ;
BY variables ;
MODEL variable distribution ;
PARMS parameter <=> number </options> ;
PREDDIST <’label’> OUTPRED=SAS-data-set <options> ;
PRIOR/HYPERPRIOR parameter distribution ;
Program statements ;
RANDOM random-effects-specification ;
UDS subroutine-name ( subroutine-argument-list) ;

The PARMS statements declare parameters in the model and assign optional starting values for the Markov chain. The PRIOR/HYPERPRIOR statements specify the prior distributions of the parameters. The MODEL statements specify the log-likelihood functions for the response variables. These statements form the basis of every Bayesian model.

In addition, you can use the ARRAY statement to define constant or parameter arrays, the BEGINCNST/ENDCNST and similar statements to save unnecessary evaluation and reduce simulation time, the PREDDIST statement to generate samples from the posterior predictive distribution, the program statements to specify more complicated models that you want to fit, and finally the UDS statements to define your own Gibbs samplers to sample any parameters in the model.

The following sections provide a description of each of these statements.