This setting lets you change the way you view articles. You can choose to have articles open in a dialog window, a new tab, or directly in the same window.
Open in Dialog
Open in New Tab
Open in same window
Open in New Tab
Open in same window
American Economic Review: Vol. 102 No. 4 (June 2012)
AER Volume. 102, Issue 4 | 
Previous ArticleNext Article
Sign up for Email Alerts Follow us on Twitter
AER Forthcoming Articles
Full-text Article
Online Appendix (144.78 KB)
Previous ArticleNext Article
Expand
Quick Tools:
Print Article Summary Email Link to this Article Export CitationSign up for Email Alerts Follow us on Twitter
Explore:
AER Forthcoming Articles
Selective Trials: A Principal-Agent Approach to Randomized Controlled Experiments
Article Citation
Chassang, Sylvain,
Gerard Padró I Miquel, and
Erik Snowberg. 2012. "Selective Trials: A Principal-Agent Approach to Randomized Controlled Experiments."
American Economic Review,
102(4): 1279-1309.
DOI: 10.1257/aer.102.4.1279
DOI: 10.1257/aer.102.4.1279
Abstract
We study the design of randomized controlled experiments when outcomes are significantly affected by experimental subjects' unobserved
effort expenditure. While standard randomized controlled trials (RCTs) are internally consistent, the unobservability of effort 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 external validity. In particular, selective trials can disentangle the effects of treatment, effort, and the interaction of treatment and effort. Moreover, they can help identify when treatment effects are affected by erroneous beliefs and inappropriate effort expenditure. (JEL C90, D82)
Article Full-Text Access
Full-text Article
Additional Materials
Online Appendix (144.78 KB)
Authors
Chassang, Sylvain (Princeton U)
Padró I Miquel, Gerard (London School of Economics)
Snowberg, Erik (CA Institute of Technology)
Padró I Miquel, Gerard (London School of Economics)
Snowberg, Erik (CA Institute of Technology)
JEL Classifications
C90: Design of Experiments: General
D82: Asymmetric and Private Information
D82: Asymmetric and Private Information
