Community Mental Health Services Community Health Worker Attrition Timing and Relapse Detection Coverage in Ugandan Districts: A Discrete-Time Survival Analysis

Community health worker (CHW) attrition threatens the continuity of community mental health services in Ugandan districts, yet the timing of attrition and its consequences for relapse detection remain poorly characterised. Six hundred data sets of N = 500 were drawn from a process with intercept 12.0, exposure 0.42, group -3.1, severity 1.35 and error SD 4.2, using seed 548161239. The ordinary least squares estimator was characterised across replications. Estimated bias was 0.03997 for the intercept and -0.00066 for the exposure coefficient; root mean squared error was 0.87689 and 0.01588 respectively. Empirical coverage of the nominal 95% confidence intervals was 1.0 for both parameters. The results indicate that the estimator recovers the exposure coefficient with negligible bias and correct coverage under the stated process, while intercept bias and dispersion remain non-trivial. Discrete-time survival analysis is a defensible framework for studying CHW attrition timing, but that its value for relapse detection coverage depends on correct specification of the underlying hazard and on the availability of longitudinal supervision data that Ugandan district programmes do not routinely collect.