Testing Theories with Learnable and Predictive Representations

Posted: 7 Mar 2012

Date Written: April 15, 2010

Abstract

We study the problem of testing an expert whose theory has a learnable and predictive parametric representation, as do standard processes used in statistics. We design a test in which the expert is required to submit a date T by which he will have learned enough to deliver a sharp, testable prediction about future frequencies. We show that this test passes an expert who knows the data-generating process and cannot be manipulated by a uninformed one. Such a test is not possible if the theory is unrestricted.

Keywords: learning, expert testing

JEL Classification: C70, D83

Suggested Citation

Al-Najjar, Nabil I. and Sandroni, Alvaro and Smorodinsky, Rann and Weinstein, Jonathan, Testing Theories with Learnable and Predictive Representations (April 15, 2010). Journal of Economic Theory, 2010. Available at SSRN: https://ssrn.com/abstract=2017478

Nabil I. Al-Najjar

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States
847-491-5426 (Phone)
847-467-1220 (Fax)

Alvaro Sandroni

University of Pennsylvania - Department of Economics ( email )

Ronald O. Perelman Center for Political Science
133 South 36th Street
Philadelphia, PA 19104-6297
United States

Northwestern University - Kellogg School of Management ( email )

2001 Sheridan Road
Evanston, IL 60208
United States
847-491-5461 (Phone)
847-467-1220 (Fax)

Rann Smorodinsky (Contact Author)

Technion-Israel Institute of Technology - The William Davidson Faculty of Industrial Engineering & Management ( email )

Haifa 32000
Israel

Jonathan Weinstein

Northwestern University - Department of Managerial Economics and Decision Sciences (MEDS) ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Register to save articles to
your library

Register

Paper statistics

Abstract Views
231
PlumX Metrics