Cost-effectiveness analysis for health communication programs.

This article describes methods for analyzing the cost-effectiveness of health communication programs, focusing in particular on estimating program effectiveness with econometric methods that address experimental and quasi-experimental designs (and their absence), national or subnational program coverage, and endogenously targeting of programs. Experimental designs provide a gold standard for assessing effectiveness but are seldom feasible for large-scale health communication programs. Even in the absence of such designs, however, fairly simple methods can be used to examine intermediate objectives, such as program reach, which in turn can be linked to program costs to estimate cost effectiveness. When moving beyond program reach to behavioral or other outcome measures, such as contraceptive use or fertility, or when faced with full-coverage national programs, more elaborate data and methods are required. We discuss data requirements and assumptions necessary in each case, focusing on single-equation multiple regression models, structural equations models, and fixed effects estimators for use with longitudinal data, and then describing how cost information can be incorporated into econometric models so as to get measures of the cost-effectiveness of communication interventions.