Testing theories with learnable and predictive representations

• 成果类型: Article
• 署名作者: Al-Najjar, Nabil I.; Sandroni, Alvaro; Smorodinsky, Rann; Weinstein, Jonathan
• 署名单位: Northwestern University; University of Pennsylvania; Technion Israel Institute of Technology
• 刊物名称: JOURNAL OF ECONOMIC THEORY
• ISSN/ISSBN: 0022-0531
• DOI: 10.1016/j.jet.2010.07.003
• 发表日期: 2010
• 页码: 2203-2217
• 关键词: Learning; Expert testing

摘要

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. (C) 2010 Elsevier Inc. All rights reserved.