Forecasting with imprecise probabilities

  • Authors:
  • Teddy Seidenfeld;Mark J. Schervish;Joseph B. Kadane

  • Affiliations:
  • Department of Statistics, Carnegie Mellon University, Pittsburgh, PA 15213, USA;Department of Statistics, Carnegie Mellon University, Pittsburgh, PA 15213, USA;Department of Statistics, Carnegie Mellon University, Pittsburgh, PA 15213, USA

  • Venue:
  • International Journal of Approximate Reasoning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We review de Finetti's two coherence criteria for determinate probabilities: coherence"1 defined in terms of previsions for a set of events that are undominated by the status quo - previsions immune to a sure-loss - and coherence"2 defined in terms of forecasts for events undominated in Brier score by a rival forecast. We propose a criterion of IP-coherence"2 based on a generalization of Brier score for IP-forecasts that uses 1-sided, lower and upper, probability forecasts. However, whereas Brier score is a strictly proper scoring rule for eliciting determinate probabilities, we show that there is no real-valued strictly proper IP-score. Nonetheless, with respect to either of two decision rules - @C-maximin or (Levi's) E-admissibility-+-@C-maximin - we give a lexicographic strictly proper IP-scoring rule that is based on Brier score.