Regression to the mean and alcohol consumption: A cohort study exploring implications for the interpretation of change in control groups in brief intervention trials

Abstract

BackgroundReductions in drinking among individuals randomised to control groups in brief alcohol intervention trials are common and suggest that asking study participants about their drinking may itself cause them to reduce their consumption. We sought to test the hypothesis that the statistical artefact regression to the mean (RTM) explains part of the reduction in such studies.Methods967 participants in a cohort study of alcohol consumption in New Zealand provided data at baseline and again six months later. We use graphical methods and apply thresholds of 8, 12, 16 and 20 in AUDIT scores to explore RTM.ResultsThere was a negative association between baseline AUDIT scores and change in AUDIT scores from baseline to six months, which in the absence of bias and confounding, is RTM. Students with lower baseline scores tended to have higher follow-up scores and conversely, those with higher baseline scores tended to have lower follow-up scores. When a threshold score of 8 was used to select a subgroup, the observed mean change was approximately half of that observed without a threshold. The application of higher thresholds produced greater apparent reductions in alcohol consumption.ConclusionsPart of the reduction seen in the control groups of brief alcohol intervention trials is likely to be due to RTM and the amount of change is likely to be greater as the threshold for entry to the trial increases. Quantification of RTM warrants further study and should assist understanding assessment and other research participation effects.

Brief Intervention Decreases Drinking Frequency in HIV-Infected, Heavy Drinking Women

“…Possible explanations for this finding include assessment reactivity and regression to the mean. 30;31 Despite drinking reductions in both groups, the intervention condition significantly decreased frequency of drinking compared to the control condition.…”

The impact of therapists’ words on the adolescent brain: In the context of addiction treatment

“…However, in contrast to expectations, youth did not show clinically significant changes in alcohol-related problems or perceived importance of changing drinking post-treatment. As youth showed clinically relevant change in one set of alcohol behaviors, but not in the other, one interpretation is that the behavior changes observed here do not simply reflect an across-the-board regression to the mean [65], but rather indicate youths’ true, but notably partial, behavior change in the context of this intervention. Another explanation for the observed treatment outcomes revolves around the persistence of alcohol-related problems.…”

The effectiveness of brief alcohol interventions delivered by community pharmacists: randomized controlled trial

“…It is highly likely that the pharmacists were under-trained in BI, and it is a study limitation that the naturalistic context precluded audiorecording. We do not interpret reductions over time as providing evidence that both groups have benefited, as change scores are inappropriate for effectiveness inferences for many reasons [38].…”