Working Paper: NBER ID: w12931
Authors: Jeffrey R. Kling
Abstract: The purpose of this article is to demonstrate how a rich array of methods can be applied to increase the relevance of field experiments in public economics. Two cross-cutting themes are important in multiple phases of the research. First, greater statistical sophistication can draw more value from a field experiment without obscuring the simple and compelling information from the differences in average outcomes of intervention and control groups. Second, the methodological frontier is interdisciplinary, drawing on knowledge and techniques developed in psychology, anthropology, and sociology that can be adapted in order to make public finance field experiments more useful.
Keywords: No keywords provided
JEL Codes: C93; H0; I0; J18
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Differences in outcomes between intervention and control groups (C90) | Estimate the causal effect of the intervention (C22) |
| Random assignment (C90) | Assess how similar groups responded to different policy interventions (J78) |
| Outcomes observed in the experimental group (C90) | Attributed to the intervention itself (C90) |
| Design of experiments (C90) | Identification of the effects of specific components of interventions (C90) |