Advertisement

De Finetti’s Methods of Elicitation

  • Joseph B. Kadane
  • Robert L. Winkler

Abstract

De Finetti (1974) uses payoffs through promissory notes, bets, or scoring rules in the elicitation of an expert’s probabilities and introduces his “hypothesis of rigidity” to argue that as long as the payoffs are small, nonlinearities in the expert’s utility function can be ignored for practical purposes. In an analysis considering not just the elicitation-related payoffs, but all uncertainties related to the expert’s fortune, we find that the hypothesis of rigidity is not sufficient to eliminate the impact of the utility function in probability elicitation. We propose an “extended hypothesis of rigidity” that adds an extra condition to de Finetti’s hypothesis. The extra assumption is that, ignoring elicitation-related payoffs, the fortune of the expert is independent of the events for which probabilities are being elicited.

Keywords

Original Hypothesis Price Ratio Elicitation Method Extra Assumption Indifference Price 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. de Finetti, B., 1974, “Theory of Probability,” Vol. 1, Wiley, New York.MATHGoogle Scholar
  2. Kadane, J.B., and Winkler, R.L., 1986, Separating probability elicitation from utilities, unpublished manuscript.Google Scholar
  3. Pratt, J.W., 1964, Risk aversion in the small and in the large, Econo-metrica, 32: 122–136.MATHGoogle Scholar
  4. Ramsey, F.P., 1931, “The Foundations of Mathematics and Other Logical Essays,” Kegan Paul, London.MATHGoogle Scholar

Copyright information

© Plenum Press, New York 1987

Authors and Affiliations

  • Joseph B. Kadane
    • 1
  • Robert L. Winkler
    • 2
  1. 1.Department of StatisticsCarnegie-Mellon UniversityPittsburghUSA
  2. 2.Fuqua School of BusinessDuke UniversityDurhamUSA

Personalised recommendations