On the Difference between Binary Prediction and True Exposure with Implications for Forecasting Tournaments and Decision Making Research

6 Pages Posted: 26 Jun 2013 Last revised: 28 Nov 2013

Nassim Nicholas Taleb

NYU-Tandon School of Engineering

Philip E. Tetlock

University of California, Berkeley - Organizational Behavior & Industrial Relations Group; University of Pennsylvania - Management Department

Date Written: November 27, 2013

Abstract

There are serious differences between predictions, bets, and exposures that have a yes/no type of payoff, the "binaries", and those that have varying payoffs, which we call the "vanilla". Real world exposures tend to belong to the vanilla category, and are poorly captured by binaries. Vanilla exposures are sensitive to Black Swan effects, model errors, and prediction problems, while the binaries are largely immune to them. The binaries are mathematically tractable, while the vanilla are much less so.  Hedging vanilla exposures with binary bets can be disastrous -- and because of the human tendency to engage in attribute substitution when confronted by difficult questions, decision-makers and researchers often confuse the vanilla for the binary.

Keywords: Predictions, Risk, Decision, Judgment and Decision Making, Fat Tails

Suggested Citation

Taleb, Nassim Nicholas and Tetlock, Philip E., On the Difference between Binary Prediction and True Exposure with Implications for Forecasting Tournaments and Decision Making Research (November 27, 2013). Available at SSRN: https://ssrn.com/abstract=2284964 or http://dx.doi.org/10.2139/ssrn.2284964

Nassim Nicholas Taleb (Contact Author)

NYU-Tandon School of Engineering ( email )

Bobst Library, E-resource Acquisitions
20 Cooper Square 3rd Floor
New York, NY 10003-711
United States

Philip E. Tetlock

University of California, Berkeley - Organizational Behavior & Industrial Relations Group ( email )

Berkeley, CA 94720
United States

University of Pennsylvania - Management Department ( email )

The Wharton School
Philadelphia, PA 19104-6370
United States

Paper statistics

Downloads
6,477
Rank
696
Abstract Views
27,017