Effective development policymaking creates a need for reliable methods of assessing effectiveness. There should be, therefore, an intimate relationship between effective policymaking and impact analysis. The goal of a development intervention defines the metric by which to assess its impact, while impact evaluation can produce reliable information on which policymakers may base decisions to modify or cancel ineffective programs and thus make the most of limited resources. This paper reviews the logic of propensity score matching (PSM) and, using data on the National Support Work Demonstration, compares that approach with other evaluation methods such as double difference, instrumental variable, and Heckman's method of selection bias correction. In addition, it demonstrates how to implement nearest-neighbor and kernel-based methods, and plot program incidence curves in E-Views. In the end, the plausibility of an evaluation method hinges critically on the correctness of the socioeconomic model underlying program design and implementation, and on the quality and quantity of available data. In any case, PSM can act as an effective adjuvant to other methods.