Dissemin is shutting down on January 1st, 2025

Links

Tools

Export citation

Search in Google Scholar

Significance test for comparing digital gene expression profiles: Partial likelihood application

This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Question mark in circle
Preprint: policy unknown
Question mark in circle
Postprint: policy unknown
Question mark in circle
Published version: policy unknown

Abstract

Most of the statistical tests currently used to detect differentially expressed genes are based on asymptotic results and may not be appropriate for low expression tags. Another problem is the common use of a single canonical cutoff, the critical level, for the p-values of all the tags, without taking into consideration the type II error and the highly variable character of the total frequency of each tag. This work reports the development of an exact significance test for comparing digital expression profiles that, in contrast to the χ 2 test, does not use asymptotic considerations. The test allows the use of a tag-customized critical significance level which minimizes a linear combination of type I and type II errors. Hence, the critical significance level is a function of the total tag expression. This feature implies that the identification of differentially expressed tags can be reliably determined, in a manner that depends on both: the p-value and the critical level calculated for each tag. We implemented this test on kemp, a C language program available under the general public license (GNU) at http://code.google. com/p/kempbasu.