The genetic overlap between smoking and a history of alcohol dependence can be assessed many different ways. One approach is to use a simple statistical model (i.e., logistic regression model), in which a respondent’s alcohol-dependence history is predicted as it relates to gender, twin-pair zygosity type (i.e., monozygotic or dizygotic), co-twin’s smoking history (i.e., current or former smoker vs. nonsmoker), and interactions between these variables.
