A generalized correlated binomial distribution with application in multiple testing problems |
| |
Authors: | Ramesh C Gupta Hui Tao |
| |
Institution: | 1. Department of Mathematics and Statistics, University of Maine, 5752 Neville Hall, Room 320, Orono, ME, 04469, USA 2. 12125 Technology Drive, MN002-0160, Eden Prairie, MN, 55344, USA
|
| |
Abstract: | A typical microarray experiment often involves comparisons of hundreds or thousands of genes. Since a large number of genes
are compared, simple use of a significance test without adjustment for multiple comparison artifacts could lead to a large
chance of false positive findings. In this context, Tsai et al. (Biometrics 59:1071–1081, 2003) have presented a model that
studies the overall error rate when testing multiple hypotheses. This model involves the distribution of the sum of non-independent
Bernoulli trials and this distribution is approximated by using a beta-binomial structure. Instead of using a beta-binomial
model, in this paper, we derive the exact distribution of the sum of non-independent and non-identically distributed Bernoulli
random variables. The distribution obtained is used to compute the conditional false discovery rates and the results are compared
to those obtained, in Table 3, by Tsai et al. (Biometrics 59:1071–1081, 2003). |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|