get_mnpp.classtree

Finds the lowest complexity parameter for a null regression tree fit

Implements methods to fit Virtual Twins models (Foster et al.
(2011) <doi:10.1002/sim.4322>) for identifying subgroups with differential
effects in the context of clinical trials while controlling the probability
of falsely detecting a differential effect when the conditional average
treatment effect is uniform across the study population using parameter
selection methods proposed in Wolf et al. (2022)
<doi:10.1177/17407745221095855>.

Jack Wolf

tehtuner

Fit and Tune Models to Detect Treatment Effect Heterogeneity

get_mnpp.classtree function

<dl><dt>z</dt>
<dd>a numeric vector of estimated CATEs from Step 1</dd>
<dt>data</dt>
<dd>a data frame containing a response, binary treatment indicators,
and covariates.</dd>
<dt>Trt</dt>
<dd>a string specifying the name of the column of <code>data</code>
contains the treatment indicators.</dd>
<dt>Y</dt>
<dd>a string specifying the name of the column of <code>data</code>
contains the response.</dd>
<dt>threshold</dt>
<dd>for "<code>step2 = 'classtree'</code>" only. The value against
which to test if the estimated individual treatment effect from Step 1 is
higher (TRUE) or lower (FALSE).</dd></dl>

Arguments

Get the MNPP for a Classification Tree — get_mnpp.classtree

<dl>

<dt>z</dt>
<dd>a numeric vector of estimated CATEs from Step 1</dd>


<dt>data</dt>
<dd>a data frame containing a response, binary treatment indicators,
and covariates.</dd>


<dt>Trt</dt>
<dd>a string specifying the name of the column of <code>data</code>
contains the treatment indicators.</dd>


<dt>Y</dt>
<dd>a string specifying the name of the column of <code>data</code>
contains the response.</dd>


<dt>threshold</dt>
<dd>for "<code>step2 = 'classtree'</code>" only. The value against
which to test if the estimated individual treatment effect from Step 1 is
higher (TRUE) or lower (FALSE).</dd>

</dl>

get_mnpp.classtree: Get the MNPP for a Classification Tree

Description

Usage

Value

Arguments