Chapter Contents
Chapter Contents
The DISCRIM Procedure

ODS Table Names

PROC DISCRIM 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 25.1: ODS Tables Produced by PROC DISCRIM
ODS Table Name Description PROC DISCRIM Option
ANOVAUnivariate statisticsANOVA
AvePostCrossValAverage posterior probabilities, cross validationPOSTERR & CROSSVALIDATE
AvePostResubAverage posterior probabilities, resubstitutionPOSTERR
AvePostTestClassAverage posterior probabilities, test classificationPOSTERR & TEST=
AveRSquareAverage R-SquareANOVA
BCorrBetween-class correlationsBCORR
BCovBetween-class covariancesBCOV
BSSCPBetween-class SSCP matrixBSSCP
BStrucBetween canonical structureCANONICAL
CanCorrCanonical correlationsCANONICAL
CanonicalMeansClass means on canonical variablesCANONICAL
ChiSqChi-square informationPOOL=TEST
ClassifiedCrossValNumber of observations and percent classified, cross validationCROSSVALIDATE
ClassifiedResubNumber of observations and percent classified, resubstitutiondefault
ClassifiedTestClassNumber of observations and percent classified, test classificationTEST=
CountsNumber of observations, variables, classes, dfdefault
CovDFDF for covariance matrices, not displayedany *COV option
DistSquared distancesMAHALANOBIS
DistFValuesF values based on squared distancesMAHALANOBIS
DistGeneralizedGeneralized squared distancesdefault
DistProbProbabilities for F values from squared distancesMAHALANOBIS
ErrorCrossValError count estimates, cross validationCROSSVALIDATE
ErrorResubError count estimates, resubstitutiondefault
ErrorTestClassError count estimates, test classificationTEST=
LevelsClass level informationdefault
LinearDiscFuncLinear discriminant functionPOOL=YES
LogDetLog determinant of the covariance matrixdefault
PCoefPooled standard canonical coefficientsCANONICAL
PCorrPooled within-class correlationsPCORR
PCovPooled within-class covariancesPCOV
PSSCPPooled within-class SSCP matrixPSSCP
PStdMeansPooled standardized class meansSTDMEAN
PStrucPooled within canonical structureCANONICAL
PostCrossValPosterior probabilities, cross validationCROSSLIST or CROSSLISTERR
PostErrCrossValPosterior error estimates, cross validationPOSTERR & CROSSVALIDATE
PostErrResubPosterior error estimates, resubstitutionPOSTERR
PostErrTestClassPosterior error estimates, test classificationPOSTERR & TEST=
PostResubPosterior probabilities, resubstitutionLIST or LISTERR
PostTestClassPosterior probabilities, test classificationTESTLIST or TESTLISTERR
RCoefRaw canonical coefficientsCANONICAL
SimpleStatisticsSimple statisticsSIMPLE
TCoefTotal-sample standard canonical coefficientsCANONICAL
TCorrTotal-sample correlationsTCORR
TCovTotal-sample covariancesTCOV
TSSCPTotal-sample SSCP matrixTSSCP
TStdMeansTotal standardized class meansSTDMEAN
TStrucTotal canonical structureCANONICAL
WCorrWithin-class correlationsWCORR
WCovWithin-class covariancesWCOV
WSSCPWithin-class SSCP matricesWSSCP

Chapter Contents
Chapter Contents

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