Estimation of long memory in volatility using wavelets

0478480 - ÚTIA 2018 RIV US eng J - Journal Article
Kraicová, Lucie - Baruník, Jozef
Estimation of long memory in volatility using wavelets.
Studies in Nonlinear Dynamics and Econometrics. Roč. 21, č. 3 (2017), č. článku 20160101. ISSN 1081-1826. E-ISSN 1558-3708
R&D Projects: GA ČR GA13-32263S
EU Projects: European Commission 612955 - FINMAP
Institutional support: RVO:67985556
Keywords : long memory * wavelets * whittle
OECD category: Applied Economics, Econometrics
Impact factor: 0.855, year: 2017
http://library.utia.cas.cz/separaty/2017/E/barunik-0478480.pdf

This work studies wavelet-based Whittle estimator of the fractionally integrated exponential gen- eralized autoregressive conditional heteroscedasticity (FIEGARCH) model often used for modeling long memory in volatility of financial assets. The newly proposed estimator approximates the spectral density using wavelet transform, which makes it more robust to certain types of irregularities in data. Based on an extensive Monte Carlo study, both behavior of the proposed estimator and its relative performance with respect to traditional estimators are assessed. In addition, we study properties of the estimators in presence of jumps, which brings interesting discussion. We find that wavelet-based estimator may become an attrac- tive robust and fast alternative to the traditional methods of estimation. In particular, a localized version of our estimator becomes attractive in small samples.
Permanent Link: http://hdl.handle.net/11104/0274595