Powered by The Ohio State University

News & Research

How Strong is the “Fake ID Effect?” An Examination Using Propensity Score Matching in Two Samples

Research has found that a bidirectional relationship exists between heavy drinking and possession of a fake ID, indicating that heavy drinking predicts one’s subsequent obtainment of a fake ID, while possession of a fake ID predicts subsequent heavy drinking. However, what is unclear is whether the fake ID is serving as a vehicle to subsequent harm (known as “the fake ID effect”) or whether those harms and outcomes are instead driven by an individual’s level of phenotypic or propensity risk. To investigate the strength of the fake ID effect, this study compared students with and without fake IDs using propensity score matching. Two samples of students were examined; the first was a cross-sectional sample of 1,454 underage college students from a large Southeastern university. The second sample was a prospective replication sample of 3,720 undergraduates under the minimum legal drinking age from a large Midwestern university, surveyed over a period of 4 years. Students in both samples completed self-report surveys that collected information with regard to frequency of binge drinking, alcohol-related problems, alcohol-related arrest/citation, marijuana use, hard drug use, and ownership of a fake ID. A number of other variables (such as demographics and exposure to substance use) were used to assess traits and risk factors for propensity scores. In the cross-sectional sample, 38.5% of students owned a fake ID. Ownership rates varied over time for the prospective sample, with a peak during students’ third year of college (39%). Prior to propensity score matching, students with fake IDs were more often binge drinkers and had greater alcohol-related problems than non-fake ID owners. After matching however, the differences were no longer significant. Alcohol-related arrests and hard drug use were associated with fake ID possession both before and after matching. Alcohol related problems, marijuana use, and frequent binge drinking differences were significant in the prospective sample, but not the cross-sectional sample.

Take away: This study supports previous findings that students with fake IDs are at higher risk for alcohol-related problems, alcohol-related arrests, and other substance use. However, this study indicates that some outcomes are largely the result of individuals’ risk traits rather than the fake ID effect. Potential interventions to address these factors may be specifically aimed at decreasing the likelihood that at-risk students obtain a fake ID. Another approach may be to incorporate fake ID intervention components into other interventions that address individuals’ traits and behaviors.


Stogner, J., Martinez, J.A., Miller, B.L., Sher, K.J. (2016) How Strong is the “Fake ID Effect?” An Examination Using Propensity Score Matching in Two Samples. Alcoholism: Clinical and Experimental Research

Leave a Reply

Notify of

Our Founding Partners