HOMEPAGE

PUBLICATION

UMDES

SAS MACROS

 

1. Studying missing data patterns.

         The macro is designed to look at missing data in four ways: the proportion of subjects with each pattern of missing data, the number and percentage of missing data for each individual variable, the concordance of missingness in any pair of variables, and possible unit nonresponse.

         The SAS macro is %missingPattern:

%missingPattern(datain=, varlist=, exclude=, missPattern1=, dataout1=, missPattern2=, dataout2=, missPattern3=, dataout3=, missPattern4=, dataout4=);

         Reference: T. Schwartz, Q. Chen, and N. Duan, (2011). Studying missing data patterns using a SAS macro, SAS Global Forum 2011 proceedings. 

         Download: macro studying missing pattern.sas

 

2. MIANALYZE for survey weighted linear regression models from multiply-imputed data.

         This macro is designed to use the MIANALYZE procedure to combine the regression coefficient estimates of survey weighted linear regression models (fitted using PROC SURVEYREG) from multiply-imputed data.

         The SAS macro is %MI_SREG:

%MI_SREG(dset, outcome, var, catVar, strata, cluster, weight, output1, output2);

         Download: MI_SREG.sas

3. MIANALYZE for survey weighted logistic regression models from multiply-imputed data.

         This macro is designed to use the MIANALYZE procedure to combine the regression coefficient estimates of survey weighted logistic regression models (fitted using PROC SURVEYLOGISTIC) from multiply-imputed data.

         The SAS macro is %MI_SLOGIT:

%MI_SLOGIT(dset, outcome, var, catVar, strata, cluster, weight, output1, output2);

         Download: MI_SLOGIT.sas

 

4. Forward stepwise selection for survey weighted logistic regression models using PROC SURVEYLOGISTIC

         The SAS macro is %SLOGIT_STEPWISE:

%SLOGIT_STEPWISE(dset, outcome, force, forceCat, varlist, catVarlist, strata, cluster, weight, alpha1, alpha2, output);

         Download: SLOGIT_STEPWISE.sas

 

 

5.     Backward selection for survey weighted linear regression models using PROC SURVEYREG

         The SAS macro is %backward:

%backward(dataset, forceInVar, varlist, catVarlist, outcome, weight, strata, cluster, alpha);

         Reference: Q. Chen and B. Gillespie, (2006). A SAS Macro for performing backward selection in PROC SURVEYREG, Midwest SAS User Group 2006 proceedings.