Asymptotically Efficient Model Selection for Panel Data Forecasting

57 Pages Posted: 5 Mar 2018 Last revised: 3 Aug 2018

Date Written: July 1, 2018

Abstract

This paper develops new model selection methods for forecasting panel data using a set of least squares (LS) vector autoregressions. Model selection is based on minimizing the estimated quadratic forecast risk among candidate models. We provide conditions under which the selection criterion is asymptotically efficient in the sense of Shibata (1980) as n (cross sections) and T (time series) approach infinity. Relative to extant selection criteria, this criterion places a heavier penalty on model dimensionality in order to account for the effects of parameterized forms of cross sectional heterogeneity (such as fixed effects) on forecast loss. We also extend the analysis to bias-corrected least squares, showing that significant reductions in forecast risk can be achieved.

Keywords: Forecasting, Model Selection, Asymptotic Efficiency, Panel Data

JEL Classification: C23, C53

Suggested Citation

Greenaway-McGrevy, Ryan, Asymptotically Efficient Model Selection for Panel Data Forecasting (July 1, 2018). Available at SSRN: https://ssrn.com/abstract=3129884 or http://dx.doi.org/10.2139/ssrn.3129884

Ryan Greenaway-McGrevy (Contact Author)

University of Auckland Business School ( email )

12 Grafton Rd
Private Bag 92019
Auckland, 1010
New Zealand

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
160
Abstract Views
508
Rank
393,991
PlumX Metrics