DEEPCAUSAL Procedure
Functional Summary
The statements and options available in the DEEPCAUSAL procedure are summarized in Table 1. The sections after the table provide a description of each statement in alphabetical order, following the PROC DEEPCAUSAL statement.
Table 1: Functional Summary
| Description | Statement | Option |
|---|---|---|
| Input Data Table Option | ||
| Specifies the input data table | PROC DEEPCAUSAL | DATA= |
Specifies the input data table for  estimation information | SCORE | INA= |
Specifies the input data table for  estimation information | SCORE | INB= |
| Specifies the input data table for outcome model information | SCORE | INO= |
| Specifies the input data table for propensity score model information | SCORE | INPS= |
| Output Data Table Options | ||
| Writes the estimation of the parameters of interest, policy evaluation, and policy comparison to an output data set | INFER | OUTEST= |
Writes the details of the estimation, including , ,  , the residual, and influence functions for each unit, to an output data set | INFER | OUTDETAILS= |
| Writes the estimation information to the specified output data set | SCORE | OUTA= |
| Writes the estimation information to the specified output data set | SCORE | OUTB= |
| Writes the outcome model information to the specified output data set | SCORE | OUTO= |
| Writes the propensity score model information to the specified output data set | SCORE | OUTPS= |
| ID Variable | ||
| Specifies the identifying variable | ID | |
| Deep Neural Network (DNN) Options | ||
| Specifies the parameters of the DNN for the propensity score model | PSMODEL | DNN= |
| Specifies the parameters of the DNN for the outcome model | MODEL | DNN= |
| Specifies the number of nodes for all hidden layers of the DNN for the propensity score model and outcome model | DNN | NODES= |
| Specifies the training options of the DNN for the propensity score model and outcome model | DNN | TRAIN= |
| Outcome Model Variables | ||
| Specifies the outcome variable | MODEL | outcome-variable |
| Specifies the covariates for the outcome model | MODEL | covariates |
| Propensity Score Model Variables | ||
| Specifies the treatment variable | PSMODEL | treatment-variable |
| Specifies the covariates for the propensity score model | PSMODEL | covariates |
| Inference Options | ||
| Specifies the list of policy variables to be evaluated | INFER | POLICY= |
| Specifies the parameters for policy comparison | INFER | POLICYCOMPARISON= |
Last updated: November 24, 2025