Bootstrap forecast intervals for asymmetric volatilities via EGARCH model

Hyeyoung Maeng; Dong Wan Shin

doi:10.1080/03610926.2015.1014105

Bootstrap forecast intervals for asymmetric volatilities via EGARCH model

Hyeyoung Maeng, Dong Wan Shin

Department of Statistics

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Bootstrap forecast intervals are developed for volatilities having asymmetric features, which are accounted for by fitting EGARCH models. A Monte-Carlo simulation compares the proposed forecast intervals with those based on GARCH fittings which ignore asymmetry. The comparison reveals substantial advantage of addressing asymmetry through EGARCH fitting over ignoring it as the conventional GARCH forecast. The EGARCH forecast intervals have empirical coverage probabilities closer to the nominal level and/or have shorter average lengths than the GARCH forecast intervals. The finding is also supported by real dataset analysis of Dow–Jones index and financial times stock exchange (FTSE) 100 index.

Original language	English
Pages (from-to)	1144-1157
Number of pages	14
Journal	Communications in Statistics - Theory and Methods
Volume	46
Issue number	3
DOIs	https://doi.org/10.1080/03610926.2015.1014105
State	Published - 1 Feb 2017

Keywords

Asymmetric volatility
bootstrapping
EGARCH model
volatility forecasting

Access to Document

10.1080/03610926.2015.1014105

Cite this

@article{36ac6c5985534d8b92d945af42412042,

title = "Bootstrap forecast intervals for asymmetric volatilities via EGARCH model",

abstract = "Bootstrap forecast intervals are developed for volatilities having asymmetric features, which are accounted for by fitting EGARCH models. A Monte-Carlo simulation compares the proposed forecast intervals with those based on GARCH fittings which ignore asymmetry. The comparison reveals substantial advantage of addressing asymmetry through EGARCH fitting over ignoring it as the conventional GARCH forecast. The EGARCH forecast intervals have empirical coverage probabilities closer to the nominal level and/or have shorter average lengths than the GARCH forecast intervals. The finding is also supported by real dataset analysis of Dow–Jones index and financial times stock exchange (FTSE) 100 index.",

keywords = "Asymmetric volatility, bootstrapping, EGARCH model, volatility forecasting",

author = "Hyeyoung Maeng and Shin, {Dong Wan}",

note = "Publisher Copyright: {\textcopyright} 2017 Taylor & Francis Group, LLC.",

year = "2017",

month = feb,

day = "1",

doi = "10.1080/03610926.2015.1014105",

language = "English",

volume = "46",

pages = "1144--1157",

journal = "Communications in Statistics - Theory and Methods",

issn = "0361-0926",

publisher = "Taylor and Francis Ltd.",

number = "3",

}

TY - JOUR

T1 - Bootstrap forecast intervals for asymmetric volatilities via EGARCH model

AU - Maeng, Hyeyoung

AU - Shin, Dong Wan

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Bootstrap forecast intervals are developed for volatilities having asymmetric features, which are accounted for by fitting EGARCH models. A Monte-Carlo simulation compares the proposed forecast intervals with those based on GARCH fittings which ignore asymmetry. The comparison reveals substantial advantage of addressing asymmetry through EGARCH fitting over ignoring it as the conventional GARCH forecast. The EGARCH forecast intervals have empirical coverage probabilities closer to the nominal level and/or have shorter average lengths than the GARCH forecast intervals. The finding is also supported by real dataset analysis of Dow–Jones index and financial times stock exchange (FTSE) 100 index.

AB - Bootstrap forecast intervals are developed for volatilities having asymmetric features, which are accounted for by fitting EGARCH models. A Monte-Carlo simulation compares the proposed forecast intervals with those based on GARCH fittings which ignore asymmetry. The comparison reveals substantial advantage of addressing asymmetry through EGARCH fitting over ignoring it as the conventional GARCH forecast. The EGARCH forecast intervals have empirical coverage probabilities closer to the nominal level and/or have shorter average lengths than the GARCH forecast intervals. The finding is also supported by real dataset analysis of Dow–Jones index and financial times stock exchange (FTSE) 100 index.

KW - Asymmetric volatility

KW - bootstrapping

KW - EGARCH model

KW - volatility forecasting

UR - http://www.scopus.com/inward/record.url?scp=84994004747&partnerID=8YFLogxK

U2 - 10.1080/03610926.2015.1014105

DO - 10.1080/03610926.2015.1014105

M3 - Article

AN - SCOPUS:84994004747

SN - 0361-0926

VL - 46

SP - 1144

EP - 1157

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

IS - 3

ER -

Bootstrap forecast intervals for asymmetric volatilities via EGARCH model

Abstract

Keywords

Access to Document

Fingerprint

Cite this