Chapter Contents
Chapter Contents
The LOGISTIC Procedure

ODS Table Names

PROC LOGISTIC assigns a name to each table it creates. You can use these names to reference the table when using the Output Delivery System (ODS) to select tables and create output data sets. These names are listed in the following table. For more information on ODS, see Chapter 15, "Using the Output Delivery System."

Table 39.2: ODS Tables Produced in PROC LOGISTIC
ODS Table Name Description Statement Option
AssociationAssociation of predicted probabilities and observed responsesMODELdefault
BestSubsetsBest subset selectionMODELSELECTION=SCORE
ClassFreqFrequency breakdown of CLASS variablesPROCSimple (with CLASS vars)
ClassLevelInfoCLASS variable levels and design variablesMODELdefault (with CLASS vars)
ClassificationClassification tableMODELCTABLE
ClassWgtWeight breakdown of CLASS variablesPROC, WEIGHTSimple (with CLASS vars)
CLOddsPLProfile likelihood confidence limits for odds ratiosMODELCLODDS=PL
CLOddsWaldWald's confidence limits for odds ratiosMODELCLODDS=WALD
CLParmPLProfile likelihood confidence limits for parametersMODELCLPARM=PL
CLParmWaldWald's confidence limits for parametersMODELCLPARM=WALD
ContrastCoeffL matrix from CONTRASTCONTRASTE
ContrastEstimateEstimates from CONTRASTCONTRASTESTIMATE=
ContrastTestWald test for CONTRASTCONTRASTdefault
ConvergenceStatusConvergence statusMODELdefault
CorrBEstimated correlation matrix of parameter estimatorsMODELCORRB
CovBEstimated covariance matrix of parameter estimatorsMODELCOVB
CumulativeModelTestTest of the cumulative model assumptionMODEL(ordinal response)
EffectNotInModelTest for effects not in modelMODELSELECTION=S/F
FastEliminationFast backward eliminationMODELSELECTION=B,FAST
FitStatisticsModel fit statisticsMODELdefault
GlobalScoreGlobal score testMODELNOFIT
GlobalTestsTest for global null hypothesisMODELdefault
GoodnessOfFitPearson and deviance goodness-of-fit testsMODELSCALE
IndexPlotsBatch capture of the index plotsMODELIPLOTS
InfluenceRegression diagnosticsMODELINFLUENCE
IterHistoryIteration historyMODELITPRINT
LackFitChiSqHosmer-Lemeshow chi-square test resultsMODELLACKFIT
LackFitPartitionPartition for the Hosmer- Lemeshow testMODELLACKFIT
LastGradientLast evaluation of gradientMODELITPRINT
LogLikeChangeFinal change in the log likelihoodMODELITPRINT
ModelBuildingSummarySummary of model buildingMODELSELECTION=B/F/S
ModelInfoModel informationPROCdefault
OddsRatiosOdds ratiosMODELdefault
ParameterEstimatesMaximum likelihood estimates of model parametersMODELdefault
ResidualChiSqResidual chi-squareMODELSELECTION=F/B
ResponseProfileResponse profilePROCdefault
SimpleStatisticsSummary statistics for explanatory variablesPROCSIMPLE
TestPrint1L[cov(b)]L' and Lb-cTESTPRINT
TestPrint2Ginv(L[cov(b)]L') and Ginv(L[cov(b)]L')(Lb-c)TESTPRINT
TestStmtsLinear hypotheses testing resultsTESTdefault
TypeIIIType III tests of effectsMODELdefault (with CLASS variables)

Chapter Contents
Chapter Contents

Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.