Virtual Twins

The Virtual Twins process fits a model to counter-factual data to find a subgroup of rows with enhanced treatment effects using a modification of the procedure of Foster et al ., (2011) ¹ . This process follows the following steps: 1. Fit a forest model to the response. 2. Compute individual treatment effects by scoring actual and counter-factual data 3. Fit a standard tree model to the estimated treatment effects.

What do I need?

One wide format data set is required to run the Virtual Twins process. This data set must contain one column containing the dependent response variable , one column containing the treatment variable, and multiple columns to be used as predictor variables.

The adsl_dii.sas7bdat data set, partially shown below, details results for 902 subjects. Subjects are listed in rows, demographic information, trial details, and findings and results are listed in columns. The ARM column lists the treatment variable. The DEATHFL column lists the dependent variable . The predictor variables are spread across 310 columns.

For detailed information about the files and data sets used or created by JMP Life Sciences software, see Files and Data Sets .

Output/Results

Refer to the Virtual Twins output documentation for detailed descriptions of the output and guides to interpreting your results.

---

1

Foster, JC, JMG Taylor, and SJ Ruberg. 2011.Subgroup identification from randomized clinical trial data. Statist. Med. 30 : 2867-2880.