Sensitivity to Distance and Baseline Distributions in Forecast Evaluation

Scoring rules can provide incentives for truthful reporting of probabilities and evaluation measures for the probabilities after the events of interest are observed. Often the space of events is ordered and an evaluation relative to some baseline distribution is desired. Scoring rules typically stud...

Full description

Saved in:
Bibliographic Details
Published in:Management science 2009-04, Vol.55 (4), p.582-590
Main Authors: Jose, Victor Richmond R, Nau, Robert F, Winkler, Robert L
Format: Article
Language:English
Subjects:
Applied sciences
baseline distributions
Business forecasting
Decision theory. Utility theory
Distribution
Distribution (Probability theory)
Economic forecasts
Exact sciences and technology
forecast verification
Forecasts
Management science
Meteorology
Methods
Operational research and scientific management
Operational research. Management science
Probabilities
Probability
Probability distributions
Probability forecasts
Probability theory
Property lines
ranked categories
scoring rules
Sensitivity analysis
sensitivity to distance
Statistical forecasts
Statistical methods
Statistical weather forecasting
Studies
Weather forecasting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Scoring rules can provide incentives for truthful reporting of probabilities and evaluation measures for the probabilities after the events of interest are observed. Often the space of events is ordered and an evaluation relative to some baseline distribution is desired. Scoring rules typically studied in the literature and used in practice do not take account of any ordering of events, and they evaluate probabilities relative to a default baseline distribution. In this paper, we construct rich families of scoring rules that are strictly proper (thereby encouraging truthful reporting), are sensitive to distance (thereby taking into account ordering of events), and incorporate a baseline distribution relative to which the value of a forecast is measured. In particular, we extend the power and pseudospherical families of scoring rules to allow for sensitivity to distance, with or without a specified baseline distribution.
ISSN:0025-1909
1526-5501
DOI:10.1287/mnsc.1080.0955