JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 183
Type: Contributed
Date/Time: Monday, July 30, 2012 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #306700
Title: Combining P-Values from Linear and Quadratic Tests for Rare Variants Provides Robust Statistics Across Genetic Models
Author(s): Lei Sun*+ and Andriy Derkach and Jerald F. Lawless
Companies: University of Toronto and University of Toronto and University of Waterloo
Address: 155 College Street, Toronto, ON, M5T 3M7, Canada
Keywords: rare variant ; robust statistics ; Fisher's method ; genetic association studies ; meta-analysis ; next generation sequencing
Abstract:

Many association tests have been proposed for rare variants, however, there is much confusion about the practical choice of a good test due to limited insights on the underlying genetic models. Recent work showed that previously proposed methods can be categorized as either linear statistics that have high power against very specific alternative hypotheses or quadratic statistics that are designed to have good power over wide ranges of alternatives. However, neither class of tests consistently outperforms the other or provides comparable power. To achieve robustness, we propose hybrid statistics that borrow strength from the two classes of tests using Fisher's method and the minimal p-value approach of combining p-values from the complementary linear and quadratic tests. Extensive simulation studies show that both methods are robust across genetic models with varying proportions of causal, deleterious and protective variants, and variant frequency and effect size. Moreover, in situations when both the linear and quadratic tests have some power, Fisher's method consistently outperforms the minimal p-value approach and has better power than both the linear and quadratic tests.


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 2012 program




2012 JSM Online Program Home

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.