The Out-of-Sample Performance of an Exact Median-Unbiased Estimator for the Near-Unity AR(1) Model

10 Pages Posted: 5 Mar 2015

See all articles by Carlos A. Medel

Carlos A. Medel

University of Nottingham

Pablo M. Pincheira

Adolfo Ibanez University - School of Business

Date Written: March 4, 2015

Abstract

We analyse the multihorizon forecasting performance of several strategies to estimate the stationary AR(1) model in a near-unity context. We focus on the Andrews' (1993) exact median-unbiased estimator (BC), the OLS estimator, and the driftless random walk (RW). In addition, we explore the forecasting performance of pairwise combinations between these individual strategies. We do this to investigate whether the Andrews' (1993) correction of the OLS downward bias helps in reducing mean squared forecast errors. Via simulations, we find that BC forecasts typically outperform OLS forecasts. When BC is compared to the RW we obtain mixed results, favouring the latter as the persistence of the true process increases. Interestingly, we also find that the combination of BC and RW performs well when the persistence of the process is high.

Keywords: Near-unity autoregression; median-unbiased estimation; unbiasedness; unit root model; forecasting; forecast combinations

JEL Classification: C22; C52; C53; C63

Suggested Citation

Medel, Carlos A. and Pincheira, Pablo M., The Out-of-Sample Performance of an Exact Median-Unbiased Estimator for the Near-Unity AR(1) Model (March 4, 2015). Available at SSRN: https://ssrn.com/abstract=2573448 or http://dx.doi.org/10.2139/ssrn.2573448

Carlos A. Medel

University of Nottingham ( email )

University Park
Nottingham, NG8 1BB
United Kingdom

Pablo M. Pincheira (Contact Author)

Adolfo Ibanez University - School of Business ( email )

Diagonal Las Torres 2640
Peñalolén
Santiago
Chile

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

Paper statistics

Downloads
20
Abstract Views
295
PlumX Metrics