Kincaid D Lawrence, Do Mai Phuong
Center for Communication Programs, Bloomberg School of Public Health, The Johns Hopkins University, Baltimore, Maryland 21205, USA.
J Health Commun. 2006;11 Suppl 2:69-90. doi: 10.1080/10810730600974522.
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.
成本效益分析基于一个简单的公式。对开展一项计划的总成本进行美元估算，然后除以预计因该计划的某些预期成果而受到影响的人数。大多数宣传活动的直接总成本通常是可得的。然而，在无法采用随机对照组设计的全面覆盖的大众媒体宣传活动中，估算仅可归因于宣传的效果量是有问题的。单方程多元回归分析可控制混杂变量，但不能充分解决因果归因问题。在本文中，多元因果归因（MCA）方法被应用于对菲律宾1516名已婚妇女的抽样调查数据，以获得可因果归因于一场全国性大众媒体宣传活动的现代避孕方法新采用者数量的有效度量，并计算其成本效益。MCA分析使用结构方程模型来检验因果路径并检验内生性，使用双变量概率分析来检验宣传活动的直接效应和内生性，以及使用倾向得分匹配来创建一个在统计上等效的匹配对照组，该对照组近似于从随机对照组设计中获得的结果。MCA结果支持以下结论：观察到的现代避孕方法使用率6.4个百分点的增长可归因于全国性大众媒体宣传活动及其对避孕态度的间接影响。这一净增长在已婚妇女群体中代表348,695名新采用者，每位新采用者的成本为1.57美元。
