A Composite Likelihood Approach Using the Evidential Paradigm to Analyze Genetic Association in Pedigrees

• Activity Number: 628
• Type: Contributed
• Date/Time: Thursday, August 2, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Zeynep Baskurt*+ and Lisa J Strug
• Companies: University of Toronto and The Hospital for Sick Children
• Keywords: Correlated Binary Data ; Evidential Paradigm ; Likelihood Paradigm ; Genetics

Abstract

Royall (1997) proposed the evidential paradigm, an alternative to Frequentist and Bayesian paradigms for interpreting data as evidence. The evidential paradigm uses the likelihood ratio (LR) for two simple hypotheses as an objective measure of the strength of statistical evidence. In genetic studies, LRs for two simple hypotheses are commonly used as a measure of evidence. However, in genetic association analysis of pedigrees, an evidential approach is not straightforward due to complex family structures. We propose to use composite likelihoods to construct LRs, and analyze case-control genetic association from the evidential perspective in families of varying size and complexities. We show how these LRs can be made robust from model misspecification; have good operational characteristics; and, for simple family structures, provide consistent results with competing methods.