October 26, 2012
College is often perceived as a risky environment for problem drinking, but recent studies indicate that individuals who attend college go on to engage in this behavior in adulthood at equal or lower rates than those who do not attend college; that is, that college may actually protect individuals from substance use behaviors in adulthood. These studies, however, often fail to account for selection bias: the fact that the people who attend college are different in many ways than people who do not attend college. In the article “Causal Inference in Latent Class Analysis,” which will appear in Structural Equation Modeling, Methodology Center researchers Stephanie Lanza and Donna Coffman implement two propensity score techniques for causal inference in latent class analysis (LCA) to determine whether college enrollment is protective or harmful for substance use behavior later in life.
LCA allows scientists to identify subgroups within a population that cannot be directly observed. By incorporating the latest causal inference techniques into LCA, scientists can examine how a risk exposure directly impacts subjects’ profiles of problem behaviors later in life. To unpack whether college really causes or insulates against future substance use problems, the authors examined data from 1092 high school seniors who participated in the National Longitudinal Survey of Youth 1979. College enrollment was assessed in 1980. In 1994, when the participants were approximately 33 years old, they were asked about their alcohol, tobacco, and drug use.
An analysis of the national population showed that if adults were not to attend college they would be over six times more likely to engage in a pattern of substance use that involves heavy drinking at age 33, compared to if they did attend. A follow-up analysis of only the individuals who did attend college showed that their rates of problem drinking in adulthood are no higher than they would have been had they not attended college. Even accounting for the differences between those who do and do not attend college, this study provides strong evidence that college enrollment does not place individuals at risk for future problem drinking.
Email firstname.lastname@example.org for an advance copy of the article