Cornell University
Search Go

Joint Computer Science & Microeconomics Workshop - Luciano Pomatto

Monday, November 13, 2017 at 4:15pm

Uris Hall, 498
Central Campus

Luciano Pomatto
California Institute of Technology

Testable Forecasts

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. These conditions have a natural Bayesian interpretation.  It is shown that optimal tests take the form of simple likelihood-ratio tests comparing forecasters’ predictions against the predictions of a hypothetical outside observer. The result rests on a novel connection between the problem of testing strategic forecasters and the classical Neyman-Pearson paradigm of hypothesis testing.

Event Type

Seminar, Class/ Workshop




economics, EconSeminar, EconMicro



Contact E-Mail

Contact Name

Amy Moesch

Contact Phone



Luciano Pomatto

Speaker Affiliation

California Institute of Technology

Open To

Cornell Economics Community (List Serve Members)

Google Calendar iCal Outlook