The GLIMMIX Procedure

Each table created by PROC GLIMMIX has a name associated with it, and you must use this name to reference the table when you use ODS statements. These names are listed in Table 27.

Table 27: ODS Tables Produced by PROC GLIMMIX

Table Name	Description	Required Statement / Option
AsyCorr	Asymptotic correlation matrix of covariance parameters	PROC GLIMMIX ASYCORR
AsyCov	Asymptotic covariance matrix of covariance parameters	PROC GLIMMIX ASYCOV
CholG	Cholesky root of the estimated matrix	RANDOM / GC
CholV	Cholesky root of blocks of the estimated matrix	RANDOM / VC
ClassLevels	Level information from the CLASS statement	Default output
Coef	matrix coefficients	E option in MODEL, CONTRAST, ESTIMATE, LSMESTIMATE, or LSMEANS; ELSM option in LSMESTIMATE
ColumnNames	Name association for OUTDESIGN data set	PROC GLIMMIX OUTDESIGN(NAMES)
CondFitStatistics	Conditional fit statistics	PROC GLIMMIX METHOD=LAPLACE
Contrasts	Results from the CONTRAST statements	CONTRAST
ConvergenceStatus	Status of optimization at conclusion	Default output
CorrB	Approximate correlation matrix of fixed-effects parameter estimates	MODEL / CORRB
CovB	Approximate covariance matrix of fixed-effects parameter estimates	MODEL / COVB
CovBDetails	Details about model-based and/or adjusted covariance matrix of fixed effects	MODEL / COVB(DETAILS)
CovBI	Inverse of approximate covariance matrix of fixed-effects parameter estimates	MODEL / COVBI
CovBModelBased	Model-based (unadjusted) covariance matrix of fixed effects if DDFM=KR or EMPIRICAL option is used	MODEL / COVB(DETAILS)
CovParms	Estimated covariance parameters in GLMMs	Default output (in GLMMs)
CovTests	Results from COVTEST statements (except for confidence bounds)	COVTEST
Diffs	Differences of LS-means	LSMEANS / DIFF (or PDIFF)
Dimensions	Dimensions of the model	Default output
Estimates	Results from ESTIMATE statements	ESTIMATE
FitStatistics	Fit statistics	Default
G	Estimated matrix	RANDOM / G
GCorr	Correlation matrix from the estimated matrix	RANDOM / GCORR
Hessian	Hessian matrix (observed or expected)	PROC GLIMMIX HESSIAN
InvCholG	Inverse Cholesky root of the estimated matrix	RANDOM / GCI
InvCholV	Inverse Cholesky root of the blocks of the estimated matrix	RANDOM / VCI
InvG	Inverse of the estimated matrix	RANDOM / GI
InvV	Inverse of blocks of the estimated matrix	RANDOM / VI
IterHistory	Iteration history	Default output
kdTree	k-d tree information	RANDOM / TYPE=RSMOOTH KNOTMETHOD= KDTREE(TREEINFO)
KnotInfo	Knot coordinates of low-rank spline smoother	RANDOM / TYPE=RSMOOTH KNOTINFO
LSMeans	LS-means	LSMEANS
LSMEstimates	Estimates among LS-means	LSMESTIMATE
LSMFtest	F test for LSMESTIMATEs	LSMESTIMATE / FTEST
LSMLines	Lines display for LS-means	LSMEANS / LINES
Margins	Predictive margins	MARGINS
MarginsDiffs	Differences of predictive margins	MARGINS / DIFF
MarginsSliceDiffs	Differences of sliced predictive margins	MARGINS / SLICEBY= SLICEDIFF=
MarginsSliceTests	Tests of sliced predictive margins	MARGINS / SLICEBY=
ModelInfo	Model information	Default output
NObs	Number of observations read and used, number of trials and events	Default output
OddsRatios	Odds ratios of parameter estimates	MODEL / ODDSRATIO
OptInfo	Optimization information	Default output
ParameterEstimates	Fixed-effects solution; overdispersion and scale parameter in GLMs	MODEL / S
ParmSearch	Parameter search values	PARMS
QuadCheck	Adaptive recalculation of quadrature approximation at solution	METHOD=QUAD(QCHECK)
ResponseProfile	Response categories and category modeled	Default output in models with binary or nominal response
Slices	Tests of LS-means slices	LSMEANS / SLICE=
SliceDiffs	Differences of simple LS-means effects	LSMEANS / SLICEDIFF=
SolutionR	Random-effects solution vector	RANDOM / S
StandardizedCoefficients	Fixed-effects solutions from centered and/or scaled model	MODEL / STDCOEF
Tests1	Type I tests of fixed effects	MODEL / HTYPE=1
Tests2	Type II tests of fixed effects	MODEL / HTYPE=2
Tests3	Type III tests of fixed effects	Default output
V	Blocks of the estimated matrix	RANDOM / V
VCorr	Correlation matrix from the blocks of the estimated matrix	RANDOM / VCORR

The SLICE statement also creates tables, which are not listed in Table 27. For information about these tables, see the section SLICE Statement in Chapter 20, Shared Concepts and Topics.