CaltechAUTHORS
  A Caltech Library Service

Testable Forecasts

Pomatto, Luciano (2019) Testable Forecasts. . (Unpublished) http://resolver.caltech.edu/CaltechAUTHORS:20190405-094352848

[img] PDF - Submitted Version
See Usage Policy.

473Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190405-094352848

Abstract

Predictions about the future are often evaluated through statistical tests. As shown by recent literature, many known tests are subject to adverse selection problems and are ineffective at discriminating between forecasters who are competent and forecasters who are uninformed but predict strategically. This paper presents necessary and sufficient conditions under which it is possible to discriminate between informed and uninformed forecasters. It is shown that optimal tests take the form of likelihood-ratio tests comparing forecasters’ predictions against the predictions of a hypothetical Bayesian outside observer. The paper also illustrates a novel connection between the problem of testing strategic forecasters and the classical Neyman-Pearson paradigm of hypothesis testing.


Item Type:Report or Paper (Working Paper)
Related URLs:
URLURL TypeDescription
http://www.its.caltech.edu/~lpomatto/testable_forecasts.pdfAuthorWorking Paper
ORCID:
AuthorORCID
Pomatto, Luciano0000-0002-4331-8436
Additional Information:I am grateful to Nabil Al-Najjar, Kim Border, Andres Carvajal, Eddie Dekel, Federico Echenique, Ithzak Gilboa, Johannes Horner, Nicolas Lambert, Wojciech Olszewski, Mallesh Pai, Larry Samuelson, Alvaro Sandroni, Colin Stewart and Max Stinchcombe for their helpful comments, and to the audiences at Yale, ASU, Caltech, UT Austin, Stanford, UC Davis, RUD, and the 5th World Congress of the Game Theory Society. I thank the Cowles Foundation for Research in Economics, where part of this research was completed, for its support and hospitality.
Funders:
Funding AgencyGrant Number
Cowles Foundation for Research in EconomicsUNSPECIFIED
Record Number:CaltechAUTHORS:20190405-094352848
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190405-094352848
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94496
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 Apr 2019 16:51
Last Modified:05 Apr 2019 16:51

Repository Staff Only: item control page