Time-Varying Window Length for Correlation Forecasts

Econometrics 2017, 5, 54: DOI at http://dx.doi.org/10.3390/econometrics5040054

29 Pages Posted: 20 Feb 2016 Last revised: 15 Dec 2020

See all articles by Yoontae Jeon

Yoontae Jeon

McMaster University - Michael G. DeGroote School of Business

Thomas H. McCurdy

University of Toronto - Rotman School of Management

Date Written: November 24, 2017

Abstract

Forecasting correlations between stocks and commodities is important for diversification across asset classes and other risk management decisions. Correlations forecasts are affected by model uncertainty, sources of which can include uncertainty about changing fundamentals and associated parameters (model instability), structural breaks and non-linearities due, for example, to regime switching. We use approaches that weight historical data according to their predictive content. Specifically, we estimate two alternative models, 'time-varying weights' and 'time-varying window' in order to maximize the value of past data for forecasting. Our empirical analyses reveal that these approaches provide superior forecasts to several benchmark models for forecasting correlations.

Keywords: Model uncertainty, variance and correlation forecasts, time-varying window length

Suggested Citation

Jeon, Yoontae and McCurdy, Thomas H., Time-Varying Window Length for Correlation Forecasts (November 24, 2017). Econometrics 2017, 5, 54: DOI at http://dx.doi.org/10.3390/econometrics5040054, Available at SSRN: https://ssrn.com/abstract=2734216 or http://dx.doi.org/10.2139/ssrn.2734216

Yoontae Jeon (Contact Author)

McMaster University - Michael G. DeGroote School of Business ( email )

1280 Main Street West
Hamilton, Ontario L8S 4M4
Canada

Thomas H. McCurdy

University of Toronto - Rotman School of Management ( email )

105 St. George Street
Toronto, Ontario M5S 3E6 M5S1S4
Canada
416-978-3425 (Phone)
416-971-3048 (Fax)

HOME PAGE: http://www-2.rotman.utoronto.ca/~tmccurdy

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
150
Abstract Views
1,068
Rank
345,924
PlumX Metrics