Year: 2006
Type: report
Abstract: Density forecasting in regression is gaining popularity as real world\napplications demand an estimate of the level of uncertainty in predictions. In\nthis paper we describe the two goals of density forecasting1 sharpness and calibration.\nWe review the evaluation methods available to a density forecaster to\nassess each of these goals and we introduce a new evaluation method that allows\nmodelers to compare and evaluate their models across both of these goals\nsimultaneously and identify the optimal model.
Authors: Michael Carney, Pádraig Cunningham
Institution: Trinity College Dublin
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2304115778
