Multigroup Equivalence Analysis for High-Dimensional Expression Data

• Main Authors: Celeste Yang, Alfred A. Bartolucci, Xiangqin Cui
• Format: Article
• Language: English
• Published: SAGE Publishing 2015-01-01
• Series: Cancer Informatics
• Online Access: https://doi.org/10.4137/CIN.S17304

Hypothesis tests of equivalence are typically known for their application in bioequivalence studies and acceptance sampling. Their application to gene expression data, in particular high-dimensional gene expression data, has only recently been studied. In this paper, we examine how two multigroup equivalence tests, the F -test and the range test, perform when applied to microarray expression data. We adapted these tests to a well-known equivalence criterion, the difference ratio. Our simulation results showed that both tests can achieve moderate power while controlling the type I error at nominal level for typical expression microarray studies with the benefit of easy-to-interpret equivalence limits. For the range of parameters simulated in this paper, the F -test is more powerful than the range test. However, for comparing three groups, their powers are similar. Finally, the two multigroup tests were applied to a prostate cancer microarray dataset to identify genes whose expression follows a prespecified trajectory across five prostate cancer stages.