Working Paper: NBER ID: w16343
Authors: Sylvain Chassang; Gerard Padro i Miquel; Erik Snowberg
Abstract: We study the design of randomized controlled experiments in environments where outcomes are significantly affected by unobserved effort decisions taken by the subjects(agents). While standard randomized controlled trials (RCTs) are internally consistent, the unobservability of effort provision compromises external validity. We approach trial design as a principal-agent problem and show that natural extensions of RCTs -which we call selective trials- can help improve the external validity of experiments. In particular, selective trials can disentangle the effects of treatment, effort, and the interaction of treatment and effort. Moreover, they can help experimenters identify when measured treatment effects are affected by erroneous beliefs and inappropriate effort provision.
Keywords: randomized controlled trials; principal-agent; selective trials; external validity
JEL Codes: C9; C90; C93; D82; O12; O22
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| unobserved effort (D29) | informativeness of RCTs (C90) |
| selective trials (C90) | disentangle effects of treatment and effort (C22) |
| selective trials (C90) | identify treatment effects influenced by erroneous beliefs (D91) |
| selective trials (C90) | improve external validity (C90) |
| selective trials (C90) | better understanding of beliefs and effort influence on treatment effects (C92) |
| treatment assignment + agents' effort levels (C78) | accurate estimations of treatment effects (C22) |