How to Improve Bayesian Reasoning: Comment on Gigerenzer and Hoffrage (1995)

Psychological Review, Vol. 106, No. 2, pp. 417-424

8 Pages Posted: 17 Feb 2010

See all articles by Barbara Mellers

Barbara Mellers

University of California, Berkeley - Marketing Group; University of Pennsylvania - Marketing Department

A. Peter McGraw

University of Colorado at Boulder - Department of Marketing

Date Written: 1999

Abstract

G. Gigerenzer and U. Hoffrage (1995) claimed that Bayesian inference problems, which have been notoriously difficult for laypeople to solve using base rates, hit rates, and false-alarm rates, become computationally simpler when information is presented with frequencies based on natural sampling. They made an evolutionary argument for the improved performance. The authors of the present article show that performance can improve with either probabilities or frequencies, depending on the rareness of the events and the type of information presented. When events are rare, probabilities are more difficult to understand than frequencies (i.e., 5 out of 1,000 vs. .005.). Furthermore, when the information is presented as joint and marginal events, nested sets become more apparent. Frequencies based on natural sampling have these desirable properties. The authors agree with Gigerenzer and Hoffrage that frequencies can improve Bayesian reasoning, but they attribute that improvement to the use of mental models that involve elements of nested sets.

Suggested Citation

Mellers, Barbara and McGraw, A. Peter, How to Improve Bayesian Reasoning: Comment on Gigerenzer and Hoffrage (1995) (1999). Psychological Review, Vol. 106, No. 2, pp. 417-424. Available at SSRN: https://ssrn.com/abstract=1554028

Barbara Mellers

University of California, Berkeley - Marketing Group ( email )

Haas School of Business
Berkeley, CA 94720
United States

University of Pennsylvania - Marketing Department

700 Jon M. Huntsman Hall
3730 Walnut Street
Philadelphia, PA 19104-6340
United States

A. Peter McGraw (Contact Author)

University of Colorado at Boulder - Department of Marketing ( email )

United States

Register to save articles to
your library

Register

Paper statistics

Downloads
122
Abstract Views
867
rank
235,469
PlumX Metrics