Advanced searches left 3/3

Categorical Data - Europe PMC

Summarized by Plex Scholar
Last Updated: 10 January 2023

* If you want to update the article please login/register

Comparison of profile-likelihood-based confidence intervals with other rank-based methods for the two-sample problem in ordered categorical data.

It has been used to determine an effect size for ordered categorical results from randomized clinical trials, the relative effect, and the likelihood that observations in one group are larger has been deemed appropriate for a measure of an effect size. Although the Wilcoxon-Mann-Whitney test is widely used to compare two groups, the null hypothesis is not limited to the relative effect of 50%, but rather the same distribution among groups. In this research, we compared actual type I error rates of the profile-likelihood-based confidence intervals for the relative effect and other rank-based simulation studies to a similar effect of 50%. And under unethical distributions, the profile-likelihood method and the Brunner-Munzel test's error rates were close to the nominal level in large or medium samples. The true type I error rates of Brunner-Munzel test were marginally higher than the nominal level, with some of the profile-likelihood test even larger.

Source link: https://europepmc.org/article/MED/36533908

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions