Linear model averaging by minimizing mean-squared forecast error unbiased estimator

Article type: Research Article

Authors: Moiseev, Nikita A.

Affiliations: Department of Mathematical Methods in Economics, Plekhanov Russian University of Economics, Moscow, Russian Federation. E-mail: [email protected]

Abstract: This paper presents a new ordinary least squares model averaging method which is proposed to be a preferable alternative to Mallows Model Averaging (MMA), Bayesian Model Averaging (BMA) and naïve simple forecast average. The method is developed to deal with possibly non-nested models and selects forecast weights by minimizing the unbiased estimator of mean-squared forecast error (MSFE). Proposed method also yields forecast confidence intervals with given significance level what is not possible when applying other model averaging methods. In addition out-of-sample simulation and empirical testing proves the supremacy of MSFE model averaging over existing combination approaches.

Keywords: Mallows information criterion, bayesian information criterion, forecast combination, model averaging, interval forecast, mean-squared forecast error model averaging

DOI: 10.3233/MAS-160376

Journal: Model Assisted Statistics and Applications, vol. 11, no. 4, pp. 325-338, 2016