Structured Analogies for Forecasting

Posted: 25 Jan 2005

See all articles by Kesten C. Green

Kesten C. Green

University of South Australia - UniSA Business; Ehrenberg-Bass Institute

J. Scott Armstrong

University of Pennsylvania - Marketing Department

Multiple version iconThere are 2 versions of this paper

Abstract

When people forecast, they often use analogies but in an unstructured manner. We propose a structured judgmental procedure that involves asking experts to list as many analogies as they can, rate how similar the analogies are to the target situation, and match the outcomes of the analogies with possible outcomes of the target. An administrator would then derive a forecast from the experts' information. We compared structured analogies with unaided judgments for predicting the decisions made in eight conflict situations. These were difficult forecasting problems; the 32% accuracy of the unaided experts was only slightly better than chance. In contrast, 46% of structured analogies forecasts were accurate. Among experts who were independently able to think of two or more analogies and who had direct experience with their closest analogy, 60% of forecasts were accurate. Collaboration did not improve accuracy.

Keywords: Forecasting, expert forecasting, judgmental procedure

Suggested Citation

Green, Kesten C. and Armstrong, J. Scott, Structured Analogies for Forecasting. Available at SSRN: https://ssrn.com/abstract=654101

Kesten C. Green (Contact Author)

University of South Australia - UniSA Business ( email )

GPO Box 2471
Adelaide, SA 5001
Australia
+61 8 83012 9097 (Phone)

HOME PAGE: http://people.unisa.edu.au/Kesten.Green

Ehrenberg-Bass Institute ( email )

Australia

HOME PAGE: http://www.marketingscience.info/people/KestenGreen.html

J. Scott Armstrong

University of Pennsylvania - Marketing Department ( email )

700 Jon M. Huntsman Hall
3730 Walnut Street
Philadelphia, PA 19104-6340
United States
215-898-5087 (Phone)
215-898-2534 (Fax)

HOME PAGE: http://marketing.wharton.upenn.edu/people/faculty/armstrong.cfm

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
567
PlumX Metrics