The application of a random effects model to censored twin data

The authors propose a random effects model to analyze the latent genetic and environmental effects on determining censored outcomes in twin studies. In this model, six normally distributed random effects are used to describe the correlation within twin pairs. The authors employ a Monte Carlo Expectation-Maximization approach for obtaining maximum likelihood estimates of fixed effects and the variances of random effects. The variances of the random effects are reparameterized to be equivalent to genetic and environmental effects in traditional twin models. The authors illustrate this model using data from the Vietnam Era Twin Registry to explore the magnitude of the genetic influence on twin similarity for the age of onset of alcohol abuse. Our results show genetic factors contribute about one third of twin similarity in the age of onset of alcohol abuse in male twins. The application of this model to twin data is discussed.