Testing Theories with Learnable and Predictive Representations

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

MoreLess

Year of publication:	2012
Authors:	Najjar, Nabil I. al- ; Sandroni, Alvaro ; Smorodinsky, Rann ; Weinstein, Jonathan
Publisher:	[S.l.] : SSRN
Subject:	Theorie \| Theory \| Lernprozess \| Learning process \| Prognose \| Forecast \| Statistischer Test \| Statistical test \| Experten \| Experts
Description of contents:	Abstract [papers.ssrn.com]