Hello, everyone! I have used bioconductor for analyzing some microarray data. Thanks to you all for the excellent work. I have a p-value adjustment question. The standard approach seems to compare the gene expression levels between cancer and normal tissues one gene at a time. The p-values can then be adjusted for multiple comparisons using the package multtest by Yongchao Ge and Sandrine Dudoit. What I am doing is to fit a logistic regression, with the cancer or normal as the binary outcome and several selected genes as the predictors. My question is how to adjust the p-value from the logitsic regression? Any help will be highly appreciated. Jason ===== Jason G. Liao, Ph.D. Division of Biometrics University of Medicine and Dentistry of New Jersey 335 George Street, Suite 2200 New Brunswick, NJ 08903-2688 phone (732) 235-8611, fax (732) 235-9777 http://www.geocities.com/jg_liao