A meta-analysis of the efficacy of remediation with drinking/driving offenders included 215 independent evaluations identified through a comprehensive literature search. Study characteristics, including dimensions of methodological quality were coded using scales and protocols developed by expert panels. Better methodological quality (as indicated by group equivalence) was associated with smaller effect size and less variation in effect size. Among studies with adequate methods (as determined empirically through examination of effect size variation with quality), the average effect of remediation on drinking/driving recidivism was an 8-9% reduction over no remediation. A similar effect size was found for alcohol involved crashes. However, licensing actions tended to be associated with reduction in occurrence of non-alcohol events (e.g. non-alcohol crashes). Exploratory regression analysis and confirmatory within study analysis suggested that combinations of modalities--in particular those including education, psychotherapy/counseling and follow-up contact/probation--were more effective than other evaluated modes for reducing drinking/driving recidivism. Treatment effects are probably underestimated in the literature due to overemphasis on education as a treatment for all offenders and drinking/driving recidivism as the most frequent measure of outcome. Limitations of the primary literature and future research needs are discussed.