"Many impact evaluations fail to provide rigorous evidence because, even when they measure changes among beneficiaries, they often cannot demonstrate that the changes were due to the program in question. One of the most common ways to estimate the impact of a program is to compare outcomes before and after a program is implemented. Yet many things change at the same time that a project is implemented, so without further information, it is not correct to assume that observed outcomes are due to the project. For example, population health status may improve after a reform of health service delivery in a particular region, but unless other competing explanations—such as changes in income, agricultural productivity, or infectious disease vectors—are ruled out, evidence of impact itself is lacking.
Improperly conducted evaluations are misleading. They present conclusions that are unsubstantiated. This means that the risk of wasting public resources or even harming participants is real. This is why clinical trials of medications have become a standard and integral part of medical care. No physician would consider prescribing strong medications whose impact and potential side-effects have not been properly evaluated. Yet in social development programs, where huge sums can be spent to modify population behaviors, change economic livelihoods, and potentially alter cultures or family structure, no such standard has been adopted. While it is widely recognized that withholding programs that are known to be beneficial would be unethical, the implicit corollary—that programs of unknown impact should not be widely replicated without proper evaluation—is frequently dismissed.”
-From “When Will We Ever Learn? Improving Lives through Impact Evaluation”