Scoring Rules for Subjective Probability Distributions

Glenn W. Harrison, Jimmy Martínez-Correa, J. Todd Swarthout, Eric R. Ulm

Research output: Working paperResearch

Abstract

The theoretical literature has a rich characterization of scoring rules for eliciting the subjective beliefs that an individual has for continuous events, but under the restrictive assumption of risk neutrality. It is well known that risk aversion can dramatically affect the incentives to correctly report the true subjective probability of a binary event, even under Subjective Expected Utility. To address this one can “calibrate” inferences about true subjective probabilities from elicited subjective probabilities over binary events, recognizing the incentives that risk averse agents have to distort reports. We characterize the comparable implications of the general case of a risk averse agent when facing a popular scoring rule over continuous events, and find that these concerns do not apply with anything like the same force. For empirically plausible levels of risk aversion, one can reliably elicit most important features of the latent subjective belief distribution without undertaking calibration for risk attitudes providing one is willing to assume Subjective Expected Utility.
Original languageEnglish
Place of PublicationAtlanta, GA
PublisherCEAR, Georgia State University
Number of pages56
Publication statusPublished - 2012
SeriesWorking paper / Center for Economic Analysis of Risk (CEAR)
Number2012-10
SeriesExCEN Working Paper
Number2013-05

Cite this

Harrison, G. W., Martínez-Correa, J., Swarthout, J. T., & Ulm, E. R. (2012). Scoring Rules for Subjective Probability Distributions. Atlanta, GA: CEAR, Georgia State University. Working paper / Center for Economic Analysis of Risk (CEAR), No. 2012-10, ExCEN Working Paper, No. 2013-05
Harrison, Glenn W. ; Martínez-Correa, Jimmy ; Swarthout, J. Todd ; Ulm, Eric R. / Scoring Rules for Subjective Probability Distributions. Atlanta, GA : CEAR, Georgia State University, 2012. (Working paper / Center for Economic Analysis of Risk (CEAR); No. 2012-10). (ExCEN Working Paper; No. 2013-05).
@techreport{924dcfedd8774296814b856aec9075de,
title = "Scoring Rules for Subjective Probability Distributions",
abstract = "The theoretical literature has a rich characterization of scoring rules for eliciting the subjective beliefs that an individual has for continuous events, but under the restrictive assumption of risk neutrality. It is well known that risk aversion can dramatically affect the incentives to correctly report the true subjective probability of a binary event, even under Subjective Expected Utility. To address this one can “calibrate” inferences about true subjective probabilities from elicited subjective probabilities over binary events, recognizing the incentives that risk averse agents have to distort reports. We characterize the comparable implications of the general case of a risk averse agent when facing a popular scoring rule over continuous events, and find that these concerns do not apply with anything like the same force. For empirically plausible levels of risk aversion, one can reliably elicit most important features of the latent subjective belief distribution without undertaking calibration for risk attitudes providing one is willing to assume Subjective Expected Utility.",
author = "Harrison, {Glenn W.} and Jimmy Mart{\'i}nez-Correa and Swarthout, {J. Todd} and Ulm, {Eric R.}",
year = "2012",
language = "English",
publisher = "CEAR, Georgia State University",
type = "WorkingPaper",
institution = "CEAR, Georgia State University",

}

Harrison, GW, Martínez-Correa, J, Swarthout, JT & Ulm, ER 2012 'Scoring Rules for Subjective Probability Distributions' CEAR, Georgia State University, Atlanta, GA.

Scoring Rules for Subjective Probability Distributions. / Harrison, Glenn W.; Martínez-Correa, Jimmy; Swarthout, J. Todd; Ulm, Eric R.

Atlanta, GA : CEAR, Georgia State University, 2012.

Research output: Working paperResearch

TY - UNPB

T1 - Scoring Rules for Subjective Probability Distributions

AU - Harrison, Glenn W.

AU - Martínez-Correa, Jimmy

AU - Swarthout, J. Todd

AU - Ulm, Eric R.

PY - 2012

Y1 - 2012

N2 - The theoretical literature has a rich characterization of scoring rules for eliciting the subjective beliefs that an individual has for continuous events, but under the restrictive assumption of risk neutrality. It is well known that risk aversion can dramatically affect the incentives to correctly report the true subjective probability of a binary event, even under Subjective Expected Utility. To address this one can “calibrate” inferences about true subjective probabilities from elicited subjective probabilities over binary events, recognizing the incentives that risk averse agents have to distort reports. We characterize the comparable implications of the general case of a risk averse agent when facing a popular scoring rule over continuous events, and find that these concerns do not apply with anything like the same force. For empirically plausible levels of risk aversion, one can reliably elicit most important features of the latent subjective belief distribution without undertaking calibration for risk attitudes providing one is willing to assume Subjective Expected Utility.

AB - The theoretical literature has a rich characterization of scoring rules for eliciting the subjective beliefs that an individual has for continuous events, but under the restrictive assumption of risk neutrality. It is well known that risk aversion can dramatically affect the incentives to correctly report the true subjective probability of a binary event, even under Subjective Expected Utility. To address this one can “calibrate” inferences about true subjective probabilities from elicited subjective probabilities over binary events, recognizing the incentives that risk averse agents have to distort reports. We characterize the comparable implications of the general case of a risk averse agent when facing a popular scoring rule over continuous events, and find that these concerns do not apply with anything like the same force. For empirically plausible levels of risk aversion, one can reliably elicit most important features of the latent subjective belief distribution without undertaking calibration for risk attitudes providing one is willing to assume Subjective Expected Utility.

M3 - Working paper

BT - Scoring Rules for Subjective Probability Distributions

PB - CEAR, Georgia State University

CY - Atlanta, GA

ER -

Harrison GW, Martínez-Correa J, Swarthout JT, Ulm ER. Scoring Rules for Subjective Probability Distributions. Atlanta, GA: CEAR, Georgia State University. 2012.