The BGLIMM Procedure

Each table that the BGLIMM procedure creates has a name that is associated with it. You must use this name to refer to the table when you use ODS statements. These names are listed in Table 18.

Table 18: ODS Tables Produced by PROC BGLIMM

Table Name	Description	Statement or Option
AutoCorr	Autocorrelation statistics for each parameter	DIAG=AUTOCORR
ClassLevels	Class level information	Default
Coef	matrix coefficients	E option in ESTIMATE or LSMEANS
CoeffPrior	Constant prior information for fixed effects	Default
CoeffPrior	Independent normal prior information for fixed effects	COEFFPRIOR=NORMAL(VAR=c)
CoeffPrior	Normal prior information for fixed effects	COEFFPRIOR=NORMAL(INPUT=SAS-data-set)
Corr	Correlation matrix of the posterior samples	STATS=CORR
Cov	Covariance matrix of the posterior samples	STATS=COV
DIC	Deviance information criterion	DIC
Diffs	Differences of LS-means	DIFF option in LSMEANS
ESS	Effective sample size for each parameter	Default
Estimates	Results from ESTIMATE statements	ESTIMATE
G	Estimated matrix	G
GCORR	Correlation matrix of the estimated matrix	GCORR
Geweke	Geweke diagnostics for each parameter	DIAG=GEWEKE
Heidelberger	Heidelberger-Welch diagnostics for each parameter	DIAG=HEIDEL
LSMeans	LS-means	LSMEANS
MCSE	Monte Carlo standard error for each parameter	DIAG=MCSE
ModelInfo	Model information	Default
NObs	Number of observations	Default
ParametersInit	Parameter initial values	INIT=PINIT
PostIntervals	Equal-tail and HPD intervals for each parameter	STATS=INT
PostSumInt	Posterior statistics for each parameter, including sample size, mean, standard deviation, and HPD intervals	Default
PostSummaries	Posterior statistics for each parameter, including sample size, mean, standard deviation, and percentiles	STATS=SUM
R	Estimated matrix	R
Raftery	Raftery-Lewis diagnostics for each parameter	DIAG=RAFTERY
REInfo	Random Effect Information	Default
RCORR	Correlation matrix of the estimated matrix	RCORR
ResponseProfile	Frequency counts for response categories	Default output in models with binary or multinomial responses
ScaleCovPrior	Priors for scale and covariance parameters	Default
WAIC	Watanabe-Akaike information criterion	WAIC