Analysis of Extreme
Drinking in Patients with Alcohol Dependence Using Pareto Regression
Sourish Das1, Ofer
Harel2, Dipak Dey2, Jonathan Covault3
and Henry Kranzler3
1SAMSI and Duke University
2Department of Statistics, University
of Connecticut, Storrs, CT
3Department of Psychiatry, University of Connecticut Health Center, CT
October
23, 2008
We developed a
novel Pareto regression model with unknown shape parameter to analyze extreme
drinking in patients with Alcohol Dependence (AD). We used a generalized linear
models (GLM) framework and a log-link between the shape parameter of the random
and systematic components and a Monte
Carlo based Bayesian method to implement the analysis.
We examined two issues of importance in the study of AD: First, we tested
whether a single nucleotide polymorphism within GABRA2 gene, which encodes a subunit of the GABAA
receptor and has been associated to AD,
influenced extreme alcohol intake and second, the efficacy of three psychotherapies
for alcoholism in treating extreme drinking behavior. European-American
participants (n = 812, 73.4% male) from Project MATCH, a multi-center randomized
clinical trial of the psychotherapeutic treatment of alcoholism, provided DNA
samples for this study. Following 3-month treatment period, during which patients
received one of the three-psychotherapy treatment, participants were followed
up at 3 month intervals. We found that women with the
high-risk GABRA2 allele had a
significantly higher probability of extreme drinking behavior than women with no high-risk allele. High-risk women also
responded to therapy better than those with two low-risk alleles.
We found that women who received cognitive
behaviorial therapy had better outcomes than
those those receiving either of the other two therapies.
Among men, there was no significant effect of GABRA2 genotype on extreme drinking behavior. However, motivational enhancement therapy was the
best treatment for the extreme drinking behavior.
Keywords: Alcohol Dependence, Bayesian Modeling, Extreme
Behavior, GABRA2, Jeffreys'
prior, Pareto Regression.