Bootstrap forecast intervals for asymmetric volatilities via EGARCH model

Hyeyoung Maeng, Dong Wan Shin

Research output: Contribution to journalArticlepeer-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 languageEnglish
Pages (from-to)1144-1157
Number of pages14
JournalCommunications in Statistics - Theory and Methods
Volume46
Issue number3
DOIs
StatePublished - 1 Feb 2017

Keywords

  • Asymmetric volatility
  • bootstrapping
  • EGARCH model
  • volatility forecasting

Fingerprint

Dive into the research topics of 'Bootstrap forecast intervals for asymmetric volatilities via EGARCH model'. Together they form a unique fingerprint.

Cite this