BACKGROUND: Anger is a frequent problem for many people with intellectual disabilities, and is often expressed as verbal and/or physical aggression. Cognitive-behaviour therapy (CBT) is the treatment of choice for common mental health problems, but CBT has only recently been adapted for people with intellectual disabilities. Anger is the main psychological presentation in which controlled trials have been used to evaluate CBT interventions for people with intellectual disabilities but these do not include rigorous randomised studies. OBJECTIVES: To evaluate (1) the impact of a staff-delivered manualised CBT anger management intervention on (a) reported anger among people with mild to moderate intellectual disabilities, and (b) anger coping skills, aggression, mental health, quality of life and costs of health and social care; (2) factors that influence outcome; and (3) the experience of service users, lay therapists and service managers. DESIGN: A cluster randomised controlled trial based on 30 day centres (15 intervention and 15 control). Intention-to-treat comparisons of outcomes used a two-level linear regression model to allow for clustering within centres with baseline outcome levels as a covariate. Comparison of cost data used non-parametric bootstrapping. Qualitative analysis used interpretative phenomenological analysis and thematic analysis. SETTING: Recruited day centres had four-plus service users with problem anger who were prepared to participate, two-plus staff willing to be lay therapists, a supportive manager and facilities for group work, and no current anger interventions. PARTICIPANTS: A total of 212 service users with problem anger were recruited. Thirty-three were deemed ineligible (30 could not complete assessments and three withdrew before randomisation). Retention at follow-up was 81%, with 17 withdrawals in each arm. Two to four staff per centre were recruited as lay therapists. Eleven service users, nine lay therapists and eight managers were interviewed. INTERVENTIONS: The manualised intervention comprised 12 weekly 2-hour group sessions supplemented by 'homework'. Lay therapists received training and ongoing supervision from a clinical psychologist. Treatment fidelity, group attendance and resources used in intervention delivery were monitored. MAIN OUTCOME MEASURES: The primary outcome was the service user-rated Provocation Index (PI), a measure of response to hypothetical situations that may provoke anger. Secondary trial outcomes were the key worker-rated PI; the service user- and key worker-rated Profile of Anger Coping Skills (PACS); the service user-rated PACS imaginal provocation test (PACS-IPT), a measure of response to actual situations known to provoke anger; aggression; mental health; self-esteem; quality of life; and health and social care resource use. Assessments were administered before randomisation and at 16 weeks and 10 months after randomisation. RESULTS: Fourteen treatment groups were delivered, each with 12 sessions lasting an average of 114 minutes, with a mean of 4.9 service users and 2.0 lay therapists. The mean hourly cost per service user was £ 25.26. The mean hourly excess cost over treatment as usual was £ 12.34. There was no effect of intervention on the primary outcome - self-rated PI. There was a significant impact on the following secondary outcomes at the 10-month follow-up: key worker-rated PI, self-rated PACS-IPT and self- and key worker-rated PACS. Key workers and home carers reported significantly lower aggression at 16 weeks, but not at 10 months. There was no impact on mental health, self-esteem, quality of life or total cost of health and social care. Service users, key workers and service managers were uniformly positive. CONCLUSIONS: The intervention was effective at changing anger coping skills and staff-rated anger. Impact on self-rated anger was equivocal. With hindsight there are reasons, from an analysis of factors influencing outcomes, to think that self-rated PI was not a well-chosen primary outcome. Widespread implementation of manualised lay therapist-led but psychologist-supervised anger management CBT for people with mild to moderate intellectual disabilities is recommended.