Cookies?
Library Header Image
LSE Research Online LSE Library Services

Interpreting the skill score form of forecast performance metrics

Wheatcroft, Edward (2019) Interpreting the skill score form of forecast performance metrics. International Journal of Forecasting, 35 (2). pp. 573-579. ISSN 0169-2070

[img] Text - Accepted Version
Repository staff only until 5 February 2021.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (361kB) | Request a copy

Identification Number: 10.1016/j.ijforecast.2018.11.010

Abstract

Performance measures of point forecasts are expressed commonly as skill scores, in which the performance gain from using one forecasting system over another is expressed as a proportion of the gain achieved by forecasting that outcome perfectly. Increasingly, it is common to express scores of probabilistic forecasts in this form; however, this paper presents three criticisms of this approach. Firstly, initial condition uncertainty (which is outside the forecaster's control) limits the capacity to improve a probabilistic forecast, and thus a ‘perfect’ score is often unattainable. Secondly, the skill score forms of the ignorance and Brier scores are biased. Finally, it is argued that the skill score form of scoring rules destroys the useful interpretation in terms of the relative skill levels of two forecasting systems. Indeed, it is often misleading, and useful information is lost when the skill score form is used in place of the original score.

Item Type: Article
Official URL: https://www.journals.elsevier.com/international-jo...
Additional Information: © 2019 Crown Copyright
Divisions: Centre for Analysis of Time Series
Subjects: Q Science > QA Mathematics
Sets: Research centres and groups > Centre for the Analysis of Time Series (CATS)
Date Deposited: 10 Dec 2018 09:44
Last Modified: 18 Jan 2020 00:02
Funders: LSE KEI Fund, Lighthill Risk Network
URI: http://eprints.lse.ac.uk/id/eprint/91134

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics