School of Economics and Finance

No. 691: Adaptive Forecasting in the Presence of Recent and Ongoing Structural Change

Liudas Giraitis , Queen Mary, University of London
George Kapetanios , Queen Mary, University of London
Simon Price , Bank of England and City University

March 1, 2012

Download full paper


We consider time series forecasting in the presence of ongoing structural change where both the time series dependence and the nature of the structural change are unknown. Methods that downweight older data, such as rolling regressions, forecast averaging over different windows and exponentially weighted moving averages, known to be robust to historical structural change, are found to be also useful in the presence of ongoing structural change in the forecast period. A crucial issue is how to select the degree of downweighting, usually defined by an arbitrary tuning parameter. We make this choice data dependent by minimizing forecast mean square error, and provide a detailed theoretical analysis of our proposal. Monte Carlo results illustrate the methods. We examine their performance on 191 UK and US macro series. Forecasts using data-based tuning of the data discount rate are shown to perform well.

J.E.L classification codes: C100, C590

Keywords:Recent and ongoing structural change, Forecast combination, Robust forecasts