I would like to thank John Pepper, Amalia Miller, and Steven Stern for invaluable support and guidance. I thank Michael Conlin, Leora Friedberg, Anup Malani, Marc Santugini, and the seminar participants at the 2008 ASHEcon Conference in Durham, NC, 2007 SEA meetings in Washington D.C., 2008 SHESG in Birmingham, AL, Michigan State University, University of Pennsylvania, and the University of Virginia for their helpful comments. I gratefully acknowledge the financial support from the Bankard Fund for Political Economy at the University of Virginia. Please address correspondence to: Jose M. Fernandez, College of Business, University of Louisville, Louisville, KY 40292. E-mail: firstname.lastname@example.org.
AN EMPIRICAL MODEL OF LEARNING UNDER AMBIGUITY: THE CASE OF CLINICAL TRIALS*
Article first published online: 17 APR 2013
© (2013) by the Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association
International Economic Review
Volume 54, Issue 2, pages 549–573, May 2013
How to Cite
Fernandez, . J. M. (2013), AN EMPIRICAL MODEL OF LEARNING UNDER AMBIGUITY: THE CASE OF CLINICAL TRIALS. International Economic Review, 54: 549–573. doi: 10.1111/iere.12006
Manuscript received April 2009; revised October 2011.
- Issue published online: 17 APR 2013
- Article first published online: 17 APR 2013
This article presents a two-dimensional structural model of learning under ambiguity in the context of clinical trials. Clinical trials offer an ideal environment to study learning under ambiguity. The randomization process found in these studies leaves patients uncertain to their actual group assignment. Therefore, patients cannot immediately attribute changes in health to the experimental drug. The article proposes the use of “learning instrumental variables” to simultaneously update patients’ beliefs of the treatment effect and group assignment. Patient learning is found to be faster when observable side effects are incorporated to account for the uncertainty in group assignment.