Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts

When predicting future events, it is common to issue forecasts that are probabilistic, in the form of probability distributions over the range of possible outcomes. Such forecasts can be evaluated using proper scoring rules. Proper scoring rules condense forecast performance into a single numerical...

Full description

Saved in:
Bibliographic Details
Main Author: Sam Allen
Format: Article
Language:English
Published: Foundation for Open Access Statistics 2024-09-01
Series:Journal of Statistical Software
Online Access:https://www.jstatsoft.org/index.php/jss/article/view/5028
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846101689276301312
author Sam Allen
author_facet Sam Allen
author_sort Sam Allen
collection DOAJ
description When predicting future events, it is common to issue forecasts that are probabilistic, in the form of probability distributions over the range of possible outcomes. Such forecasts can be evaluated using proper scoring rules. Proper scoring rules condense forecast performance into a single numerical value, allowing competing forecasters to be ranked and compared. To facilitate the use of scoring rules in practical applications, the scoringRules package in R provides popular scoring rules for a wide range of forecast distributions. This paper discusses an extension to the scoringRules package that additionally permits the implementation of popular weighted scoring rules. Weighted scoring rules allow particular outcomes to be targeted during forecast evaluation, recognizing that certain outcomes are often of more interest than others when assessing forecast quality. This introduces the potential for very flexible, user-oriented evaluation of probabilistic forecasts. We discuss the theory underlying weighted scoring rules, and describe how they can readily be implemented in practice using scoringRules. Functionality is available for weighted versions of several popular scoring rules, including the logarithmic score, the continuous ranked probability score, and the energy score. Two case studies are presented to demonstrate this, whereby weighted scoring rules are applied to univariate and multivariate probabilistic forecasts in the fields of meteorology and economics.
format Article
id doaj-art-40d221ece6804ffdb05a58f0c097e715
institution Kabale University
issn 1548-7660
language English
publishDate 2024-09-01
publisher Foundation for Open Access Statistics
record_format Article
series Journal of Statistical Software
spelling doaj-art-40d221ece6804ffdb05a58f0c097e7152024-12-29T00:12:41ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602024-09-01110110.18637/jss.v110.i08Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic ForecastsSam Allen0ETH Zürich When predicting future events, it is common to issue forecasts that are probabilistic, in the form of probability distributions over the range of possible outcomes. Such forecasts can be evaluated using proper scoring rules. Proper scoring rules condense forecast performance into a single numerical value, allowing competing forecasters to be ranked and compared. To facilitate the use of scoring rules in practical applications, the scoringRules package in R provides popular scoring rules for a wide range of forecast distributions. This paper discusses an extension to the scoringRules package that additionally permits the implementation of popular weighted scoring rules. Weighted scoring rules allow particular outcomes to be targeted during forecast evaluation, recognizing that certain outcomes are often of more interest than others when assessing forecast quality. This introduces the potential for very flexible, user-oriented evaluation of probabilistic forecasts. We discuss the theory underlying weighted scoring rules, and describe how they can readily be implemented in practice using scoringRules. Functionality is available for weighted versions of several popular scoring rules, including the logarithmic score, the continuous ranked probability score, and the energy score. Two case studies are presented to demonstrate this, whereby weighted scoring rules are applied to univariate and multivariate probabilistic forecasts in the fields of meteorology and economics. https://www.jstatsoft.org/index.php/jss/article/view/5028
spellingShingle Sam Allen
Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
Journal of Statistical Software
title Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
title_full Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
title_fullStr Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
title_full_unstemmed Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
title_short Weighted scoringRules: Emphasizing Particular Outcomes When Evaluating Probabilistic Forecasts
title_sort weighted scoringrules emphasizing particular outcomes when evaluating probabilistic forecasts
url https://www.jstatsoft.org/index.php/jss/article/view/5028
work_keys_str_mv AT samallen weightedscoringrulesemphasizingparticularoutcomeswhenevaluatingprobabilisticforecasts