A Multiplicative Error Model with Heterogeneous Components for Forecasting Realized Volatility. (12th February 2015)

• Record Type: Journal Article
• Authors: Han, Heejoon; Park, Myung D.; Zhang, Shen
• Is Part Of: Journal of forecasting. Volume 34:Number 3(2015:Apr.)
• Page Start: 209
• Page End: 219
• Publication Date: 2015-02-12
• Subjects: Forecasting -- Periodicals; Forecasting -- Mathematical models -- Periodicals; 003.2
• DOI: 10.1002/for.2333
• Languages: English
• ISSNs: 0277-6693

Abstract

<abstract abstract-type="main" id="for2333-abs-0001"> <title> <x xml:space="preserve">Abstract</x> </title> <p id="for2333-para-0004">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 &amp; Sons, Ltd.</p> </abstract>