Community Mental Health Services Peer-Supervision Dosage and Relapse Detection Latency in Ghanaian Districts: A Stepped-Wedge Implementation Evaluation

Peer supervision is widely promoted as a low-cost strategy for strengthening community mental health services in low-resource settings, yet the minimum supervision dosage needed to detect relapse reliably remains unspecified. The analysis used a declared variance structure with between-cluster standard deviation of 6.0, residual standard deviation of 4.5, and intraclass correlation of 0.64, and estimated power across 2000 replications per design cell for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. Power rose steeply with cluster count and effect size, and 56 clusters were required to achieve 80% power for a 5-percentage-point effect. Minimum detectable effect at 80% power fell from approximately 9 percentage points with 8 clusters to approximately 4 percentage points with 32 clusters. The findings indicate that stepped-wedge evaluations of peer-supervision dosage in Ghanaian districts are feasible only at cluster counts substantially larger than those typically deployed, and that underpowered designs risk misclassifying effective supervision schedules as ineffective.