Measuring the Completeness of Theories

37 Pages Posted: 16 Aug 2017 Last revised: 28 Sep 2019

See all articles by Drew Fudenberg

Drew Fudenberg

Massachusetts Institute of Technology (MIT)

Jon Kleinberg

Cornell University - Department of Computer Science

Annie Liang

University of Pennsylvania - Department of Economics

Sendhil Mullainathan

Harvard University - Department of Economics; National Bureau of Economic Research (NBER)

Date Written: April 23, 2019

Abstract

We use machine learning to provide a tractable measure of the amount of predictable variation in the data that a theory captures, which we call its "completeness." We apply this measure to three problems: assigning certain equivalents to lotteries, initial play in games, and human generation of random sequences. We discover considerable variation in the completeness of existing models, which sheds light on whether to focus on developing better models with the same features or instead to look for new features that will improve predictions. We also illustrate how and why completeness varies with the experiments considered, which highlights the role played in choosing which experiments to run.

Keywords: Prediction, Randomness Perception, Theory Completeness

JEL Classification: C10, C52, C92, D9

Suggested Citation

Fudenberg, Drew and Kleinberg, Jon and Liang, Annie and Mullainathan, Sendhil, Measuring the Completeness of Theories (April 23, 2019). PIER Working Paper No. 18-010. Available at SSRN: https://ssrn.com/abstract=3018785 or http://dx.doi.org/10.2139/ssrn.3018785

Drew Fudenberg

Massachusetts Institute of Technology (MIT) ( email )

77 Massachusetts Avenue
50 Memorial Drive
Cambridge, MA 02139-4307
United States

Jon Kleinberg

Cornell University - Department of Computer Science ( email )

4130 Upson Hall
Ithaca, NY 14853-7501
United States

Annie Liang (Contact Author)

University of Pennsylvania - Department of Economics ( email )

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

Sendhil Mullainathan

Harvard University - Department of Economics ( email )

Littauer Center
Cambridge, MA 02138
United States
617-496-2720 (Phone)
617-495-7730 (Fax)

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States
617-588-1473 (Phone)
617-876-2742 (Fax)

Register to save articles to
your library

Register

Paper statistics

Downloads
564
Abstract Views
2,026
rank
48,426
PlumX Metrics