simulation3

Provides inference for the Wilcoxon-Mann-Whitney test under the null hypothesis H0: AUC = 0.5 for continuous, discrete or mixed random variables. Traditional implementations test H0: F = G, which is inappropriately broad and leads to erroneous inferences. Methods are described in M. Grendar (2025) "Wilcoxon-Mann-Whitney Test of No Group Discrimination" <doi:10.48550/arXiv.2511.20308>.

Marian Grendar

wmwAUC

Wilcoxon-Mann-Whitney Test of No Group Discrimination

simulation3 function

A list containing simulation results (N=500, n=300):<dl>
<dt>wmw_ci</dt>
<dd>95% confidence intervals obtained by pseudomedian_ci()</dd><dt>wt_ci</dt>
<dd>95% confidence intervals obtained by wilcox.test()</dd><dt>eauc</dt>
<dd>Values of eAUC</dd><dt>pseudomedian</dt>
<dd>Values of the pseudomedian</dd>
</dl>

Format

Synthetic data — simulation3

A list containing simulation results (N=500, n=300):<dl>
<dt>wmw_ci</dt>
<dd>95% confidence intervals obtained by pseudomedian_ci()</dd>

<dt>wt_ci</dt>
<dd>95% confidence intervals obtained by wilcox.test()</dd>

<dt>eauc</dt>
<dd>Values of eAUC</dd>

<dt>pseudomedian</dt>
<dd>Values of the pseudomedian</dd>


</dl>

simulation3: Synthetic data

Description

Usage

Arguments

Format