The
Optimal Treatment Regime
follows the methodology of Zhang
et al
., (2012)
1
, fitting both a response
regression
model and a propensity score logistic model to the input data set. It combines results from these
model
fits to compute a
pseudo binary response
and
weight
(located in the output data in the
Z_AIPWE
, and
W_AIPWE columns
, respectively) that are suitable for input to predictive modeling routines. A contrast response (located in
C_AIPWE
) is also computed, and it can also be modeled or used directly to assign optimal treatment.
One
wide
format data set is required to run the
Optimal Treatment Regime
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
.
Refer to the
Optimal Treatment Regime
output documentation for detailed descriptions of the output and guides to interpreting your results.
Zhang, B, AA Tsiatis, M Davidian, M Zhang, and E Laber. 2012. Estimating optimal treatment regimes from a classification perspective.
Stat
1
: 103-114.