Shared Statistical Concepts

The ID statement lists one or more variables from the input data set that are transferred to output data sets that are created by high-performance statistical procedures, provided that the output data set contains one (or more) records per input observation. For example, when an OUTPUT statement is used to produce observationwise scores or prediction statistics, ID variables are added to the output data set.

By default, high-performance statistical procedures do not include all variables from the input data set in output data sets. In the following statements, a logistic regression model is fit and then scored. The input and output data are stored in the Greenplum database. The output data set contains three columns (p, account, trans_date) where p is computed during the scoring process and the account and transaction date are transferred from the input data set. (High-performance statistical procedures also transfer any distribution keys from the input to the output data.)

libname GPLib greenplm server=gpdca user=XXX password=YYY
              database=ZZZ;
proc hplogistic data=gplib.myData;
   class a b;
   model y = a b x1-x20;
   output out=gplib.scores pred=p;
   id account trans_date;
run;