Abstract
Randomized field experiments can provide trustworthy evidence about the effects of interventions. But, investigators have limited control over important features of the field experiment (e.g., program implementation, receipt of intended and unintended services, retention of participants in the study). Unchecked, these factors can limit the technical adequacy and utility of the study. In the absence of direct control over these factors, efforts should be directed at developing valid indicators so their influence can be taken into account using advanced analytical techniques. Coupled with logical and statistical analyses, studies that cast a wider measurement net should provide more useful explanations for the pattern of observed effects.
Get full access to this article
View all access options for this article.
