pre_sens

Run sensitivity analysis on pre-test design

A set of tools to implement the non-parametric bounds and Bayesian methods for assessing post-treatment bias developed in Blackwell, Brown, Hill, Imai, and Yamamoto (2025) <doi:10.1017/pan.2025.3>.

Matthew Blackwell

prepost

Non-Parametric Bounds and Gibbs Sampler for Assessing Priming
and Post-Treatment Bias

Jacob Brown

Sophie Hill

Kosuke Imai

Teppei Yamamoto

pre_sens function

<dl><dt>formula</dt>
<dd>A formula with syntax <code>y ~ t</code>, where <code>y</code> is the
(unquoted) name of the outcome and <code>t</code> is the (unquoted) name of the treatment.</dd>
<dt>data</dt>
<dd>A data.frame containing variables in the formula, moderator, and covariates arguments.</dd>
<dt>moderator</dt>
<dd>A one-sided formuala with syntax <code>~ d</code>, where <code>d</code>
is the (unquoted) name of the moderator variable for the CATE.</dd>
<dt>t_by</dt>
<dd>Numeric indicating the grid spacing for the
\(\theta\) parameter that restricts what proportion of units have
their outcomes affected by the pre vs post-measurement of the
moderator.</dd>
<dt>conf_level</dt>
<dd>A numeric indicating the confidence level for the bootstrap
confidence intervals.</dd>
<dt>outcome_mono</dt>
<dd>A integer indicating the direction of the priming
monotonicity assumption. The default value <code>1</code> indicates that asking the
moderator question in the pre-test moves outcomes in a positive direction
for all units. The value <code>-1</code> indicates it moves outcomes in a negative
direction for all units.</dd></dl>

Arguments

Run sensitivity analysis on pre-test design — pre_sens

<dl>

<dt>formula</dt>
<dd>A formula with syntax <code>y ~ t</code>, where <code>y</code> is the
(unquoted) name of the outcome and <code>t</code> is the (unquoted) name of the treatment.</dd>


<dt>data</dt>
<dd>A data.frame containing variables in the formula, moderator, and covariates arguments.</dd>


<dt>moderator</dt>
<dd>A one-sided formuala with syntax <code>~ d</code>, where <code>d</code>
is the (unquoted) name of the moderator variable for the CATE.</dd>


<dt>t_by</dt>
<dd>Numeric indicating the grid spacing for the
\(\theta\) parameter that restricts what proportion of units have
their outcomes affected by the pre vs post-measurement of the
moderator.</dd>


<dt>conf_level</dt>
<dd>A numeric indicating the confidence level for the bootstrap
confidence intervals.</dd>


<dt>outcome_mono</dt>
<dd>A integer indicating the direction of the priming
monotonicity assumption. The default value <code>1</code> indicates that asking the
moderator question in the pre-test moves outcomes in a positive direction
for all units. The value <code>-1</code> indicates it moves outcomes in a negative
direction for all units.</dd>

</dl>

pre_sens: Run sensitivity analysis on pre-test design

Description

Usage

Value

Arguments

Examples