|
Organizers |
Simultaneous Confidence Intervals for Odds Ratios in Candidate Gene Studies.
by
Melinda H McCann
Oklahoma State University (Department of Statistics; Stillwater, OK 74078)
Coauthors: Stephanie A. Monks; Oklahoma State University;
Mailing address: Department of Statistics; Oklahoma State University; Stillwater, OK 74078; email:stephanie.monks@okstate.edu
Candidate gene studies routinely involve construction of multiple confidence intervals for odds ratios for the various haplotypes. Confidence intervals are often preferred to hypothesis tests so that the practical significance of any observed significances can also be determined. Unfortunately, these one-at-a-time intervals are often utilized to make overall conclusions, such as that one particular haplotype has the largest odds of disease. Overall conclusions such as these require an adjustment for multiplicity. We provide several methods which adjust for multiplicity and compare their performance.
Date received: July 11, 2007
Copyright © 2007 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # caur-61.