The HPGENSELECT Procedure
CODE <options> ;
The CODE statement enables you to write SAS DATA step code for computing predicted values of the fitted model either to a file or to a catalog entry. This code can then be included in a DATA step to score new data.
Table 4.2 summarizes the options available in the CODE statement.
Table 4.2: CODE Statement Options
|
Option |
Description |
|---|---|
|
CATALOG= in SAS/STAT 12.3 User's Guide |
Names the catalog entry where the generated code is saved |
|
DUMMIES in SAS/STAT 12.3 User's Guide |
Retains the dummy variables in the data set |
|
ERROR in SAS/STAT 12.3 User's Guide |
Computes the error function |
|
FILE= in SAS/STAT 12.3 User's Guide |
Names the file where the generated code is saved |
|
FORMAT= in SAS/STAT 12.3 User's Guide |
Specifies the numeric format for the regression coefficients |
|
GROUP= in SAS/STAT 12.3 User's Guide |
Specifies the group identifier for array names and statement labels |
|
IMPUTE in SAS/STAT 12.3 User's Guide |
Imputes predicted values for observations with missing or invalid covariates |
|
LINESIZE= in SAS/STAT 12.3 User's Guide |
Specifies the line size of the generated code |
|
LOOKUP= in SAS/STAT 12.3 User's Guide |
Specifies the algorithm for looking up CLASS levels |
|
RESIDUAL in SAS/STAT 12.3 User's Guide |
Computes residuals |
For more information about the syntax of the CODE statement, see the section CODE Statement in SAS/STAT 12.3 User's Guide.
The HPGENSELECT procedure supports the IMPUTE option only for multinomial, binomial, and binary distributions.