The SEVSELECT Procedure
Input Data Tables
PROC SEVSELECT accepts DATA= and INEST= data tables as input data tables. This section details the information that they are expected to contain.
DATA= Data Table
The DATA= data table is expected to contain the values of the analysis variables that you specify in the CLASS, EFFECT, LOSS, and SCALEMODEL statements.
If you specify the BY statement, then the DATA= data table must contain all the BY variables that you specify in the BY statement. However, it is not required to be sorted by the BY variables.
INEST= Data Table
The INEST= data table is expected to contain the initial values of the parameters for the parameter estimation process.
If you specify the BY statement, then the INEST= data table must contain all the BY variables that you specify in the BY statement. The data table is not required to be sorted by BY variables, and it is not required to contain all the BY groups present in the DATA= data table. For the BY groups that are not present in the INEST= data table, the default parameter initialization method is used.
The INEST= data table must be created by using the OUTEST= option in a PROC SEVSELECT step that uses the same BY and SCALEMODEL statements as the PROC SEVSELECT step where you specify the INEST= option.