vimp_ci

Compute confidence intervals for the true variable importance parameter.

Calculate point estimates of and valid confidence intervals for
nonparametric, algorithm-agnostic variable importance measures in high and low dimensions,
using flexible estimators of the underlying regression functions. For more information
about the methods, please see Williamson et al. (Biometrics, 2020),  Williamson et al. (JASA, 2021), and Williamson and Feng (ICML, 2020).

Brian D. Williamson

vimp

Perform Inference on Algorithm-Agnostic Variable Importance

Jean Feng

Charlie Wolock

Noah Simon

Marco Carone

vimp_ci function

<dl><dt>est</dt>
<dd>estimate of variable importance, e.g., from a call to <code>vimp_point_est</code>.</dd>
<dt>se</dt>
<dd>estimate of the standard error of <code>est</code>, e.g., from a call to <code>vimp_se</code>.</dd>
<dt>scale</dt>
<dd>scale to compute interval estimate on (defaults to "identity": compute Wald-type CI).</dd>
<dt>level</dt>
<dd>confidence interval type (defaults to 0.95).</dd>
<dt>truncate</dt>
<dd>truncate CIs to have lower limit at (or above) zero?</dd></dl>

Arguments

Confidence intervals for variable importance — vimp_ci

<dl>

<dt>est</dt>
<dd>estimate of variable importance, e.g., from a call to <code>vimp_point_est</code>.</dd>


<dt>se</dt>
<dd>estimate of the standard error of <code>est</code>, e.g., from a call to <code>vimp_se</code>.</dd>


<dt>scale</dt>
<dd>scale to compute interval estimate on (defaults to "identity": compute Wald-type CI).</dd>


<dt>level</dt>
<dd>confidence interval type (defaults to 0.95).</dd>


<dt>truncate</dt>
<dd>truncate CIs to have lower limit at (or above) zero?</dd>

</dl>

vimp_ci: Confidence intervals for variable importance

Description

Usage

Value

Arguments

Details