Trauma-Informed Care Protocol Mismatch and Mental Health Symptom Exacerbation in Kenyan Psychiatric Wards: A Difference-in-Differences Analysis of Restraint Policy Adoption

Kenyan psychiatric wards have adopted trauma-informed restraint policies unevenly, and the resulting mismatch between protocol and ward practice may worsen mental health symptoms. Power was estimated 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. The analysis found that 50 clusters are required to detect a 5-percentage-point effect at 80% power, and that power falls steeply below 24 clusters. The intraclass correlation of 0.64 dominates the design, making cluster-level randomisation essential and ward-level confounding a first-order threat. Difference-in-differences designs for restraint policy adoption must be powered at the cluster level, not the patient level, and that protocol mismatch should be operationalised as a ward-level exposure rather than an individual-level covariate. The contribution is a design template for evaluating trauma-informed care rollouts in low-resource psychiatric settings where randomisation is infeasible.