Attrition Bias in a U.S. Internet Survey of Alcohol Use Among College Freshmen

Abstract

ABSTRACT. Objective: Attrition bias is an important issue in survey research on alcohol, tobacco, and other drug use. The issue is even more salient for Internet studies, because these studies often have higher rates of attrition than face-to-face or telephone surveys, and there is limited research examining the issue in the fi eld of drug usage, specifi cally for college underclassmen. This study assessed whether measures of highrisk drinking and alcohol-related consequences were related to attrition groups ("stayers" or "leavers") in a cohort of college freshmen. Method: Data were collected in 2003 and 2004 from 2,144 fi rst-year college students at 10 universities in the southeastern United States. Demographics, indicators of high-risk drinking, and alcohol-related consequences were compared between cohort stayers and leavers in statistical analyses using two methods. Results: Analyses indicated that cohort leavers reported signifi cantly higher levels of high-risk drinking (past-30-day heavy episodic drinking, weekly drunkenness) and past-30-day smoking but not signifi cantly increased alcohol-related consequences. The directionality of bias was modestly consistent across outcomes and comparison methods. Conclusions: The current study's fi ndings suggest that intervention efforts to reduce smoking or high-risk drinking need to consider attrition bias during study follow-up or account for it in analyses. (J. Stud. Alcohol Drugs 70: [606][607][608][609][610][611][612][613][614] 2009)

Implications of Attrition in a Longitudinal Web-Based Survey: An Examination of College Students Participating in a Tobacco Use Study

“…At the individual level, many of our findings were consistent with previous literature. For instance, higher odds of nonresponse were seen in blacks and in men; similar results that have been replicated in many different samples of college students [ 17 , 23 - 25 ]. We also found that, compared with those seeking an advanced degree, those seeking a bachelor’s degree–but not those seeking an associate’s degrees–were more likely to be lost at follow-up, indicating a curvilinear relationship.…”

Marijuana use trajectories and academic outcomes among college students

“…Marijuana use may have been underreported (Akinci et al, 2001; Delaney-Black et al, 2010; Gruenwald and Johnson, 2006; Wagenaar et al, 1993), although measuring drug use in a school or research setting is more likely to produce honest responses (Kandel et al, 2006). The sample may also be subject to selection bias, given that substance users may have been less likely to continue participation in the study (McCoy et al, 2008). …”

Impact of a U.S. antismoking national media campaign on beliefs, cognitions and quit intentions

“…Second, although follow-up data are weighted to account for its effects, sample attrition limits these data. Studies show that online surveys suffer from greater respondent attrition than other types of studies [45, 46] but that attrition does not necessarily indicate bias [47]. Third, observed dose-response effects are based on self-reported measure of exposure, which can be subject to selective attention biases.…”