Chapter Contents
Chapter Contents
The TRANSREG Procedure


                     < OUTTEST=SAS-data-set > < a-options > < o-options > ;

The PROC TRANSREG statement starts the TRANSREG procedure. Optionally, this statement identifies an input and an OUTTEST= data set, specifies the algorithm and other computational details, requests displayed output, and controls the contents of the OUT= data set (which is created with the OUTPUT statement). The DATA= and OUTTEST= options can appear only in the PROC TRANSREG statement.

The following table summarizes options available in the PROC TRANSREG statement. All a-options and o-options are described in the sections on either the MODEL or OUTPUT statement, in which these options can also be specified.

Table 65.1: Options Available in the TRANSREG Procedure
Task Option Statement
Identify input data set  
specifies input SAS data setDATA=PROC
Output data set with test statistics  
specifies output test statistics data setOUTTEST=PROC
Input data set  
specifies input observation typeTYPE=MODEL
restarts iterationsREITERATEMODEL
Specify method and control iterations  
specifies minimum criterion changeCCONVERGE=MODEL
specifies minimum data changeCONVERGE=MODEL
specifies canonical dummy-variable initializationDUMMYMODEL
specifies maximum number of iterationsMAXITER=MODEL
specifies iterative algorithmMETHOD=MODEL
specifies number of canonical variablesNCAN=MODEL
specifies singularity criterionSINGULAR=MODEL
Control missing data handling  
includes monotone special missing valuesMONOTONE=MODEL
excludes observations with missing valuesNOMISSMODEL
unties special missing valuesUNTIE=MODEL
Control intercept and CLASS variables  
CLASS dummy variable name prefixCPREFIX=MODEL
CLASS dummy variable label prefixLPREFIX=MODEL
no intercept or centeringNOINTMODEL
order of class variable levelsORDER=MODEL
controls output of reference levelsREFERENCE=MODEL
CLASS dummy variable label separatorsSEPARATORS=MODEL
Control displayed output  
confidence limits alphaALPHA=MODEL
displays parameter estimate confidence limitsCLMODEL
displays model specification detailsDETAILMODEL
displays iteration historiesHISTORYMODEL
suppresses displayed outputNOPRINTMODEL
suppresses the iteration historiesSHORTMODEL
displays regression resultsSS2MODEL
displays ANOVA tableTESTMODEL
displays conjoint part-worth utilitiesUTILITIESMODEL
Control standardization  
fits additive modelADDITIVEMODEL
do not zero constant variablesNOZEROCONSTANTMODEL
specifies transformation standardizationTSTANDARD=MODEL
Predicted values, residuals, scores  
outputs canonical scoresCANONICALOUTPUT
outputs individual confidence limitsCLIOUTPUT
outputs mean confidence limitsCLMOUTPUT
specifies design matrix codingDESIGN=OUTPUT
outputs leverageLEVERAGEOUTPUT
does not restore missing valuesNORESTOREMISSINGOUTPUT
suppresses output of scoresNOSCORESOUTPUT
outputs predicted valuesPREDICTEDOUTPUT
outputs redundancy variablesREDUNDANCY=OUTPUT
outputs residualsRESIDUALSOUTPUT
Output data set replacement  
replaces dependent variablesDREPLACEOUTPUT
replaces independent variablesIREPLACEOUTPUT
replaces all variablesREPLACEOUTPUT
Output data set coefficients  
outputs coefficientsCOEFFICIENTSOUTPUT
outputs ideal point coordinatesCOORDINATESOUTPUT
outputs marginal meansMEANSOUTPUT
outputs redundancy analysis coefficientsMREDUNDANCYOUTPUT
Output data set variable name prefixes  
dependent variable approximationsADPREFIX=OUTPUT
independent variable approximationsAIPREFIX=OUTPUT
canonical dependent variablesCDPREFIX=OUTPUT
conservative individual lower CLCILPREFIX=OUTPUT
canonical independent variablesCIPREFIX=OUTPUT
conservative-individual-upper CLCIUPREFIX=OUTPUT
conservative-mean-lower CLCMLPREFIX=OUTPUT
conservative-mean-upper CLCMUPREFIX=OUTPUT
liberal-individual-lower CLLILPREFIX=OUTPUT
liberal-individual-upper CLLIUPREFIX=OUTPUT
liberal-mean-lower CLLMLPREFIX=OUTPUT
liberal-mean-upper CLLMUPREFIX=OUTPUT
predicted valuesPPREFIX=OUTPUT
redundancy variablesRPREFIX=OUTPUT
transformed dependentsTDPREFIX=OUTPUT
transformed independentsTIPREFIX=OUTPUT
Output data set macros  
creates macro variablesMACROOUTPUT
Output data set details  
dependent and independent approximationsAPPROXIMATIONSOUTPUT
canonical correlation coefficientsCCCOUTPUT
canonical elliptical point coordinateCECOUTPUT
canonical point coordinatesCPCOUTPUT
canonical quadratic point coordinatesCQCOUTPUT
approximations to transformed dependentsDAPPROXIMATIONSOUTPUT
approximations to transformed independentsIAPPROXIMATIONSOUTPUT
elliptical point coordinatesMECOUTPUT
point coordinatesMPCOUTPUT
quadratic point coordinatesMQCOUTPUT
multiple regression coefficientsMRCOUTPUT

specifies the SAS data set to be analyzed. If you do not specify the DATA= option, PROC TRANSREG uses the most recently created SAS data set. The data set must be an ordinary SAS data set; it cannot be a special TYPE= data set.

specifies an output data set to contain hypothesis tests results. When you specify the OUTTEST= option, the data set contains ANOVA results. When you specify the SS2 a-option, regression tables are also output. When you specify the UTILITIES o-option, conjoint analysis part-worth utilities are also output.

Chapter Contents
Chapter Contents

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