Artificial Intelligence Causal Estimation of Insecticide-Treated Net Distribution Effect on Malaria Incidence Under Variable Campaign Ledger Geocoding Error: A Doubly Robust Evaluation of Healthcare Targeting Equity

Campaign ledgers that record insecticide-treated net distribution frequently carry geocoding errors, and these errors are not independent of the healthcare access they are used to evaluate. The design is a before-after-control-impact (BACI) estimator with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64; 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 is methodological and uses no observational data: it reports the operating characteristics of the proposed design rather than an estimated effect on malaria incidence. Under the declared variance structure, 54 clusters are required to detect a 5 percentage point effect at 80 per cent power, and the minimum detectable effect falls steeply as cluster count rises from 8 to 32. The framework proposes that targeting-equity claims drawn from campaign ledgers are defensible only when the geocoding-error mechanism is modelled explicitly and the design is powered for the smallest effect the equity claim requires.