Statistical Modelling 6 (2006), 352–372
Bayesian modeling for genetic association in case-control studies:
accounting for unknown population substructure
Li Zhang, Bhramar Mukherjee, Malay Ghosh, and Rongling Wu
Department of Statistics
University of Florida
P.O. Box 118545
Gainesville, FL 32611-8545
USA
eMail:
mukherjee@stat.ufl.edu
Abstract:
A two-stage parametric Bayesian method is proposed to examine the
association between a candidate gene and the occurrence of a disease
after accounting for population substructure. This procedure,
implemented via a Markov chain Monte Carlo numerical integration
technique, first estimates the posterior probability of different
unknown population substructures and then integrates this information
into a disease-gene association model through the technique of
Bayesian model averaging. The model relaxes certain assumptions
of previous analyses and provides a unified computational framework
to obtain an estimate of the log odds ratio parameter corresponding
to the genetic factor after allowing for the allele frequencies to
vary across subpopulations. The uncertainty in estimating the population
substructure is taken into account while providing credible intervals
for parameters in the disease-gene association model. Simulations on
unmatched case-control studies that mimic an admixed Argentinean
population are performed to demonstrate the statistical properties
of our model. The method is also applied to a real data set coming
from a genetic association study on obesity.
Keywords:
Bayesian model averaging; gene-disease association;
linkage equilibrium; Markov chain Monte Carlo; obesity
Downloads:
Data
and software in zipped archive
back