JSM 2004 - Toronto

Abstract #301466

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 184
Type: Topic Contributed
Date/Time: Tuesday, August 10, 2004 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics in Epidemiology
Abstract - #301466
Title: Omnibus Tests in Case Control Association Studies of Candidate Genes
Author(s): Bingshu E. Chen*+ and Philip S. Rosenberg
Companies: National Cancer Institute and National Cancer Institute
Address: 6120 Executive Blvd. EPS/8047, Rockville, MD, 20852,
Keywords: sase control study ; genetic epidemiology ; Omnibus Test ; single nucleotide polymorphisms
Abstract:

In case control studies, it is of interest to investigate the association between disease and candidate genes. In a candidate gene analysis, when disease susceptibility is conferred by a SNP, the SNP-by-SNP test with false discovery rate (FDR) controlling multiple comparison procedure often has higher power than the Haplotype Frequency Test (HFT). However, the HFT may have higher power when disease susceptibility is conferred by a haplotype. We develop an Omnibus Test to address this model selection problem. Let p1 be the minimum adjusted p value of SNP-by-SNP FDR, and let p2 be the p value of the HFT. The Omnibus Test is constructed from p3 = min(p1, p2). A challenge arises because the distribution of p3 is unknown. Two approaches are considered: Bonferroni correction and permutation test. Simulation studies show that both Omnibus Tests have reasonable Type I error; the permutation test is more powerful. The Omnibus Tests successfully address the under-power problem of each procedure when the true genetic model favors the other: the power obtained by the Omnibus Test is close to the more powerful of the component test statistics p1 and p2.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004