A Multiplicative Error Model with Heterogeneous Components for Forecasting Realized Volatility

Journal of Forecasting - Tập 34 Số 3 - Trang 209-219 - 2015
Heejoon Han1, Myung D. Park2, Shen Zhang3
1Department of Economics, Sungkyunkwan University, Seoul, Republic of Korea
2Korea Energy Economics Institute, Ulsan, Republic of Korea
3SCAPE, Department of Economics, National University of Singapore

Tóm tắt

To forecast realized volatility, this paper introduces a multiplicative error model that incorporates heterogeneous components: weekly and monthly realized volatility measures. While the model captures the long‐memory property, estimation simply proceeds using quasi‐maximum likelihood estimation. This paper investigates its forecasting ability using the realized kernels of 34 different assets provided by the Oxford‐Man Institute's Realized Library. The model outperforms benchmark models such as ARFIMA, HAR, Log‐HAR and HEAVY‐RM in within‐sample fitting and out‐of‐sample (1‐, 10‐ and 22‐step) forecasts. It performed best in both pointwise and cumulative comparisons of multi‐step‐ahead forecasts, regardless of loss function (QLIKE or MSE). Copyright © 2015 John Wiley & Sons, Ltd.

Từ khóa


Tài liệu tham khảo

10.1007/978-3-540-71297-8_24

10.1111/1468-0262.00418

10.1162/rest.89.4.701

Andersen TG, 2009, Handbook of Financial Econometrics, 67

10.3982/ECTA6495

10.1111/j.1368-423X.2008.00275.x

Brownlees CT, 2011, Handbook of Volatility Models and their Applications, 281

10.1198/jasa.2010.ap09039

10.1353/mcb.2005.0027

10.1093/jjfinec/nbp001

Diebold FX, Comparing predictive accuracy, Journal of Business and Economic Statistics, 13, 253, 10.1080/07350015.1995.10524599

Doornik JA andMOoms.A package for estimating forecasting and simulating Arfima models: Arfima package 1.0 for Ox Erasmus University 1999.

10.2202/1558-3708.1218

10.1002/jae.683

10.1016/j.jeconom.2005.01.018

10.2307/2999632

10.1093/jjfinec/nbt023

10.1080/07350015.2014.897954

10.1016/j.jeconom.2005.01.005

Heber G, 2009, OMI's Realized Library,

10.1080/07474938.2010.481554

10.1093/jjfinec/nbl001

10.1016/j.jeconom.2010.03.034

10.1007/978-3-540-71297-8_36

10.1016/j.ijforecast.2009.01.008

10.1002/jae.1158

10.2307/2171956