The GLIMMIX Procedure
-
Overview
-
Getting Started
-
SyntaxPROC GLIMMIX StatementBY StatementCLASS StatementCODE StatementCONTRAST StatementCOVTEST StatementEFFECT StatementESTIMATE StatementFREQ StatementID StatementLSMEANS StatementLSMESTIMATE StatementMODEL StatementNLOPTIONS StatementOUTPUT StatementPARMS StatementRANDOM StatementSLICE StatementSTORE StatementWEIGHT StatementProgramming StatementsUser-Defined Link or Variance Function
-
DetailsGeneralized Linear Models TheoryGeneralized Linear Mixed Models TheoryGLM Mode or GLMM ModeStatistical Inference for Covariance ParametersDegrees of Freedom MethodsEmpirical Covariance ("Sandwich") EstimatorsExploring and Comparing Covariance MatricesProcessing by SubjectsRadial Smoothing Based on Mixed ModelsOdds and Odds Ratio EstimationParameterization of Generalized Linear Mixed ModelsResponse-Level Ordering and ReferencingComparing the GLIMMIX and MIXED ProceduresSingly or Doubly Iterative FittingDefault Estimation TechniquesDefault OutputNotes on Output StatisticsODS Table NamesODS Graphics
-
ExamplesBinomial Counts in Randomized BlocksMating Experiment with Crossed Random EffectsSmoothing Disease Rates; Standardized Mortality RatiosQuasi-likelihood Estimation for Proportions with Unknown DistributionJoint Modeling of Binary and Count DataRadial Smoothing of Repeated Measures DataIsotonic Contrasts for Ordered AlternativesAdjusted Covariance Matrices of Fixed EffectsTesting Equality of Covariance and Correlation MatricesMultiple Trends Correspond to Multiple Extrema in Profile LikelihoodsMaximum Likelihood in Proportional Odds Model with Random EffectsFitting a Marginal (GEE-Type) ModelResponse Surface Comparisons with Multiplicity AdjustmentsGeneralized Poisson Mixed Model for Overdispersed Count DataComparing Multiple B-SplinesDiallel Experiment with Multimember Random EffectsLinear Inference Based on Summary DataWeighted Multilevel Model for Survey Data
- References
The ID statement specifies which quantities to include in the OUT= data set from the OUTPUT statement in addition to any statistics requested in the OUTPUT statement. If no ID statement is given, the GLIMMIX procedure includes all variables from the input data set in the OUT= data set. Otherwise, only the variables listed in the ID statement are included. Automatic variables such as _LINP_, _MU_, _VARIANCE_, etc. are not transferred to the OUT= data set unless they are listed in the ID statement.
The ID statement can be used to transfer computed quantities that depend on the model to an output data set. In the following
example, two sets of Hessian weights are computed in a gamma regression with a noncanonical link. The covariance matrix for
the fixed effects can be constructed as the inverse of 
. 
is a diagonal matrix of the 
or 
, depending on whether the expected or observed Hessian matrix is desired, respectively.
proc glimmix;
class group age;
model cost = group age / s error=gamma link=pow(0.5);
output out=gmxout pred=pred;
id _variance_ wei woi;
vpmu = 2*_mu_;
if (_mu_ > 1.0e-8) then do;
gpmu = 0.5 * (_mu_**(-0.5));
gppmu = -0.25 * (_mu_**(-1.5));
wei = 1/(_phi_*_variance_*gpmu*gpmu);
woi = wei + (cost-_mu_) *
(_variance_*gppmu + vpmu*gpmu) /
(_variance_*_variance_*gpmu*gpmu*gpmu*_phi_);
end;
run;
The variables _VARIANCE_ and _MU_ and other symbols are predefined by PROC GLIMMIX and can be used in programming statements. For rules and restrictions, see the section Programming Statements.