Multivariate Causal Attribution and Cost-Effectiveness of a National Mass Media Campaign in the Philippines

Abstract

Cost-effectiveness analysis is based on a simple formula. A dollar estimate of the total cost to conduct a program is divided by the number of people estimated to have been affected by it in terms of some intended outcome. The direct, total costs of most communication campaigns are usually available. Estimating the amount of effect that can be attributed to the communication alone, however is problematical in full-coverage, mass media campaigns where the randomized control group design is not feasible. Single-equation, multiple regression analysis controls for confounding variables but does not adequately address the issue of causal attribution. In this article, multivariate causal attribution (MCA) methods are applied to data from a sample survey of 1,516 married women in the Philippines to obtain a valid measure of the number of new adopters of modern contraceptives that can be causally attributed to a national mass media campaign and to calculate its cost-effectiveness. The MCA analysis uses structural equation modeling to test the causal pathways and to test for endogeneity, biprobit analysis to test for direct effects of the campaign and endogeneity, and propensity score matching to create a statistically equivalent, matched control group that approximates the results that would have been obtained from a randomized control group design. The MCA results support the conclusion that the observed, 6.4 percentage point increase in modern contraceptive use can be attributed to the national mass media campaign and to its indirect effects on attitudes toward contraceptives. This net increase represented 348,695 new adopters in the population of married women at a cost of U.S. $1.57 per new adopter.

Estimating the impact of antenatal care visits on institutional delivery in India: A propensity score matching analysis

“…The impact of ANC visits for a woman i, noted δ i , is defined as the difference between the potential outcome in the presence of and the potential outcome in the absence of ANC visits An alternative solution to the multiple regression analysis, is matching methods, which compare outcomes for exposed and unexposed individuals with similar observed characteristics or similar likelihoods of being exposed [18][19][20]. However, the limitation of this method is that matching treatment and control individuals becomes increasingly difficult as the number of covariates on which matching is intended increases.…”

A Framework for Health Communication Across the HIV Treatment Continuum

“…203 ART literacy, to better understand the negative association between CD4 (high is good) and viral load (high is bad) and appreciate the need for repeated viral load testing could be successfully addressed by combining interpersonal approaches at the facility and community levels with mass media, providing the added benefit of disseminating consistent information to multiple audiences at a large scale and in a cost-effective manner. 204 A multifaceted approach can also be used to address HIV-related stigma through messages that are educational, persuasive, and destigmatizing. For the policy level, communication interventions focused on advocacy support updating, implementation, and dissemination of such policies.…”

Propensity score matching in estimating the effect of managerial education on academic planning behavior. Study design: a cross-sectional study

“…It has been well recognized among researchers and evaluators that calculating effectiveness is the most important part, but is sometimes the most challenging [8]. One can not claim a particular amount of behavior change without a causal attribution.…”

“…Many education and communication scholars have concluded therefore that it is virtually impossible to draw such a causal inference [9]. Without such a capability, how can we ever justify the influence of an education program?…”

“…To assess the impact of an education program, researchers and evaluators may adopt different methods. Among these, PSM is highly recommended as it is one of the strong statistical techniques [6-8,10,11] as to be discussed. This method can help to reduce selection bias as it allows for quasi-experimental contrasts between students in receiving "treatment" and "control" groups based on their observed characteristics.…”