Department of Biostatistics Seminar/Workshop Series

A parametric model to estimate the proportion from true null using a distribution for p-values

Chang Yu, PhD

Associate Professor

Department of Biostatistics, Vanderbilt University School of Medicine

Microarray studies generate a large number of p-values from comparisons of many genes. The estimate of the proportion of the p-values sampled from the null hypothesis draws a broad interest. The two-component mixture model is often used to estimate this proportion. If the data are generated under the null hypothesis, the p-values follow the uniform distribution. What is the distribution of p-values when data are sampled from the alternative hypothesis? This work derives this distribution for the chi-squared test. Using this distribution, we develop a parametric model to estimate the proportion of p-values sampled from the null hypothesis.

Simulation studies were conducted to evaluate its performance in comparison with five recent methods. Even in scenarios with clusters of correlated p-values and a multi-component mixture in the alternative, our method had a robust performance. We demonstrate our method on a real microarray dataset.
Topic revision: r1 - 29 Oct 2015, AshleeBartley
 

This site is powered by FoswikiCopyright © 2013-2017 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki? Send feedback