The authors used individual and group‐level variables within age and sex to predict drinking patterns over time among individuals. Eight longitudinal samples of persons age 21–30 years were analyzed separately. Drinking patterns at final measurement were regressed simultaneously on both individual and group‐level variables. The first model tested for marital and drinking status along with group‐level mean change in drinking. The second model tested for marital and drinking status along with group‐percent married. The third model tested for marital and drinking status along with percent newly married. Using meta‐analysis, the authors demonstrated significant and homogeneous effects for the three models tested and for grouplevel mean differences in the first model.
No takes yet. Share an insight, caveat, or question.
Leino et al. (1995) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: