Testing theories with learnable and predictive representations

Nabil I. Al-Najjar*, Alvaro Sandroni, Rann Smorodinsky, Jonathan Weinstein

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)2203-2217
Number of pages15
JournalJournal of Economic Theory
Volume145
Issue number6
DOIs
StatePublished - Nov 1 2010

Keywords

  • Expert testing
  • Learning

ASJC Scopus subject areas

  • Economics and Econometrics

Fingerprint Dive into the research topics of 'Testing theories with learnable and predictive representations'. Together they form a unique fingerprint.

Cite this