A likelihood ratio and Markov chain‐based method to evaluate density forecasting. (24th June 2019)

• Record Type: Journal Article
• Authors: Li, Yushu; Andersson, Jonas
• Is Part Of: Journal of forecasting. Volume 39:Number 1(2020)
• Page Start: 47
• Page End: 55
• Publication Date: 2019-06-24
• Subjects: density forecasting -- likelihood ratio test -- Markov chain; Forecasting -- Periodicals; Forecasting -- Mathematical models -- Periodicals; 003.2
• DOI: 10.1002/for.2604
• Languages: English
• ISSNs: 0277-6693

Abstract

Abstract: In this paper, we propose a likelihood ratio‐based method to evaluate density forecasts, which can jointly evaluate the unconditional forecasted distribution and dependence of the outcomes. Unlike the well‐known Berkowitz test, the proposed method does not require a parametric specification of time dynamics. We compare our method with the method proposed by several other tests and show that our methodology has very high power against both dependence and incorrect forecasting distributions. Moreover, the loss of power, caused by the nonparametric nature of the specification of the dynamics, is shown to be small compared to the Berkowitz test, even when the parametric form of dynamics is correctly specified in the latter method.