Premium
IMPROVING FORECAST ACCURACY BY COMBINING RECURSIVE AND ROLLING FORECASTS *
Author(s) -
Clark Todd E.,
McCracken Michael W.
Publication year - 2009
Publication title -
international economic review
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.658
H-Index - 86
eISSN - 1468-2354
pISSN - 0020-6598
DOI - 10.1111/j.1468-2354.2009.00533.x
Subject(s) - monte carlo method , variance (accounting) , regular polygon , computer science , scalar (mathematics) , mathematical optimization , scheme (mathematics) , mean squared error , econometrics , forecast error , algorithm , mathematics , statistics , economics , mathematical analysis , geometry , accounting
This article presents analytical, Monte Carlo, and empirical evidence on combining recursive and rolling forecasts when linear predictive models are subject to structural change. Using a characterization of the bias–variance trade‐off faced when choosing between either the recursive and rolling schemes or a scalar convex combination of the two, we derive optimal observation windows and combining weights designed to minimize mean square forecast error. Monte Carlo experiments and several empirical examples indicate that combination can often provide improvements in forecast accuracy relative to forecasts made using the recursive scheme or the rolling scheme with a fixed window width.