Background and aimsWithin many alcohol prevention interventions, changes in alcohol‐related attitudes (ARA) are often proposed as precursors to changes in drinking behaviour. This study aimed to measure the longitudinal relationship between ARA and behaviour during the implementation of a large‐scale prevention trial.Design and settingThis study was a two‐arm school‐based clustered randomized controlled trial. A total of 105 schools in Northern Ireland and Scotland participated in the Steps Towards Alcohol Misuse Prevention Programme (STAMPP) Trial.ParticipantsA sample of 12 738 pupils (50% female; mean age = 12.5 years at baseline) self‐completed questionnaires on four occasions (T1–T4). The final data sweep (T4) was 33 months post baseline.MeasurementsIndividual assessments of ARA and heavy episodic drinking (HED) were made at each time‐point. Additional covariates included location, school type, school socio‐economic status and intervention arm. Estimated models examined the within‐individual autoregressive and cross‐lagged effects between ARA and HED across the four time‐points (Bayes estimator).FindingsAll autoregressive effects were statistically significant for both ARA and HED across all time‐points. Past ARA predicted future ARA [e.g. ARAT1 → ARAT2 = 0.071, credibility interval (CI) = 0.043–0.099, P < 0.001, one‐tailed]. Similarly, past HED predicated future HED (e.g. HEDT1 → HEDT2 = 0.303, CI = 0.222–0.382, P < 0.001, one‐tailed). Autoregressive effects for HED were larger than those for ARA at all time‐points. In the cross‐lagged effects, past HED statistically significantly predicted more positive ARA in the future (e.g. HEDT2 → ARAT3 = 0.125, CI = 0.078–0.173, P < 0.001, one tailed) except for the initial T1–T2 path. In contrast, past ARA did not predict future HED across any time‐points.ConclusionsChanges in alcohol‐related attitudes were not a precursor to changes in heavy episodic drinking within the Steps Towards Alcohol Misuse Prevention Programme (STAMPP) Trial in Scotland and Northern Ireland. Rather, alcohol‐related attitudes were more likely to reflect prior drinking status than predict future status. Heavy episodic drinking status appears to have a greater impact on future alcohol attitudes than attitudes do on future heavy episodic drinking.