The CAUSALTRT Procedure

specifies a number to be used as the level for % confidence limits in the "Analysis of Causal Effect" table. The number must be between 0 and 1. This number is also used as the default level for propensity score and outcome model confidence limits. For the propensity score and outcome models, you can override this default level by specifying the ALPHA= options in the MODEL and PSMODEL statements, respectively. By default, ALPHA=0.05, which results in 95% confidence intervals.

estimates the average treatment effect for the treated. When this option is applied, it replaces the default estimation of the average treatment effect (ATE). For more information about the estimation methods implemented in the CAUSALTRT procedure and for comparisons between the average treatment effect and average treatment effect for the treated, see the sections Estimating the Average Treatment Effect for the Treated (ATT) and Causal Effects: Definitions, Assumptions, and Identification. This option can be used only when METHOD=IPWR or REGADJ.

computes weighted and unweighted standardized mean differences (between treatment and control conditions) and variance ratios (treatment to control) for the covariates (effects) in the propensity score model. This option is supported only for estimation methods that fit a propensity score model.

The results are displayed in the "Covariate Differences for Propensity Score Model" table. This table also includes columns for the weighted and unweighted mean and variance for propensity score model effects within each treatment condition; these columns are not displayed but are accessible if you save the table as an output data set by specifying the ODS OUTPUT statement. You can display these columns by modifying the corresponding template.

names the SAS data set that contains the data to be analyzed. If you omit this option, the procedure uses the most recently created SAS data set.

sorts the levels of the outcome variable for a binary model in reverse of the specified order.

specifies the method to use to estimate the potential outcomes and treatment effect. You can specify one of the following values:

For all estimation methods, you specify the outcome variable in the MODEL statement and the treatment variable in the PSMODEL statement. For more information about the estimation methods that the CAUSALTRT procedure implements, see the sections Estimating the Average Treatment Effect (ATE) and Estimating the Average Treatment Effect for the Treated (ATT).

specifies the maximum length of effect names in tables and output data sets to be n characters, where n is a value between 20 and 128. By default, NAMELEN=20.

specifies options for the nonlinear optimization methods that are used for fitting the specified models. You can specify one or more of the following nlo-options separated by spaces:

suppresses the display of all output that involves the outcome variable. This option is useful for investigating the balance of covariates between treatment conditions by exploring different propensity score models before displaying estimates for the causal effect. This option is effective only when METHOD=IPW, IPWR, or IPWS.

suppresses all displayed output. This option temporarily disables the Output Delivery System (ODS). For more information, see Chapter 23, Using the Output Delivery System.

specifies the sort order for the levels of the classification variables (which are specified in the CLASS statement).

This option applies to the levels for all classification variables, except when you use the (default) ORDER=FORMATTED option with numeric classification variables that have no explicit format. In that case, the levels of such variables are ordered by their internal value.

The ORDER= option can take the following values:

By default, ORDER=FORMATTED. For ORDER=FORMATTED and ORDER=INTERNAL, the sort order is machine-dependent.

For more information about sort order, see the chapter on the SORT procedure in the Base SAS Procedures Guide and the discussion of BY-group processing in the "Grouping Data" section of SAS Programmers Guide: Essentials.

displays all optional output.

controls plots that are produced through ODS Graphics. For more information about controlling specific plots, see also the PLOTS options in the BOOTSTRAP and PSMODEL statements.

ODS Graphics must be enabled before plots can be requested. For example:

ods graphics on;

proc causaltrt plots=all method=ipwr;
   model y;
   psmodel trt = x1 x2;
run;

ods graphics off;

For more information about enabling and disabling ODS Graphics, see the section Enabling and Disabling ODS Graphics in Chapter 24, Statistical Graphics Using ODS.

You can specify the following plot-requests:

You can specify the following global-plot-options:

displays parameter estimates for the outcome models for the control and treatment conditions.

displays parameter estimates for the propensity score model.

specifies the sort order for the levels of the outcome variable. In order for this option to apply, either the outcome variable must be specified in the CLASS statement or the DIST=BIN option must be specified in the MODEL statement. The following table shows how PROC CAUSALTRT interprets values of the RORDER= option.

By default, RORDER=FORMATTED. The DESCENDING option in the PROC CAUSALTRT statement causes the response variable to be sorted in reverse of the order displayed in the previous table. For more information about sort order, see the chapter on the SORT procedure in the Base SAS Procedures Guide.

specifies the tolerance for testing the singularity of a matrix, where tolerance must be between 0 and 1. By default, tolerance is 1E7 times the machine epsilon.

specifies the number of threads for analytic computations and overrides the SAS system option THREADS | NOTHREADS. If you do not specify the THREADS= option or if you specify THREADS=0, the number of threads is determined from the number of CPUs in the host on which the analytic computations execute.