Drinking buddies and their prospective influence on alcohol outcomes: alcohol expectancies as a mediator

Abstract

The process by which peers or the social network influence individual alcohol use, particularly among adults, remains a necessary area of research. The purpose of the present study was to examine the longitudinal influence of "drinking buddies" on alcohol outcomes (i.e., alcohol use, heavy drinking, and alcohol-related problems) as mediated by alcohol expectancies of social facilitation. Participants were 1347 (men = 660, women = 687) newly married individuals recruited from the community. They were assessed at the time of marriage and through the fourth wedding anniversary. Longitudinal mediation across time was evaluated using latent growth modeling. Overall, the prospective association between the number of drinking buddies in the social network and all three alcohol outcomes was mediated by alcohol expectancies. In testing group invariance across gender, findings suggest that social-facilitation expectancies may be more relevant to men than women in predicting typical alcohol use and alcohol-related problems. Given that the social network may impact alcohol use at least in part through social expectancies, tailoring alcohol interventions to modify these specific beliefs may be particularly beneficial. In addition, strategies that target drinkers' social networks or their drinking buddies specifically may be useful.

Figure 1

Piecewise growth modeling for each construct, where the intercept factor captures the baseline values for the construct, slope 1 captures growth to time 2, slope 2 captures growth to time 3, and slope 4 captures growth to time 4. Though not pictured, the intercept and slopes were allowed to correlate within a construct, as well as all intercepts across constructs.

Figure 2

Longitudinal mediation across four time waves: Examining alcohol expectancies as a mediator on the relationship between number of drinking buddies and typical alcohol use. CI = 95% bias-corrected bootstrapped confidence intervals. Though not pictured, intercepts were allowed to correlate. *p < .05. **p < .01.

Figure 3

Longitudinal mediation across four time waves: Examining alcohol expectancies as a mediator on the relationship between number of drinking buddies and heavy alcohol use. CI = 95% bias-corrected bootstrapped confidence intervals. Though not pictured, intercepts were allowed to correlate. *p < .05. **p < .01.

Figure 4

Longitudinal mediation across four time waves: Examining alcohol expectancies as a mediator on the relationship between number of drinking buddies and alcohol-related problems. CI = 95% bias-corrected bootstrapped confidence intervals. Though not pictured, intercepts were allowed to correlate. *p < .05. **p < .01.