Finite-sample Properties of Maximum Likelihood and Whittle Estimators in EGARCH and FIEGARCH Models

  1. Perez, Ana 1
  2. Zaffaroni, Paolo 2
  1. 1 Universidad de Valladolid
    info

    Universidad de Valladolid

    Valladolid, España

    ROR https://ror.org/01fvbaw18

  2. 2 Imperial College London
    info

    Imperial College London

    Londres, Reino Unido

    ROR https://ror.org/041kmwe10

Revue:
Quantitative and Qualitative Analysis in Social Sciences

ISSN: 1752-8925

Année de publication: 2008

Volumen: 2

Número: 1

Type: Article

GOOGLE SCHOLAR lock_openAccès ouvert editor

D'autres publications dans: Quantitative and Qualitative Analysis in Social Sciences

Résumé

EGARCH models for conditionally heteroscedastic time series have attracted a steadily increasing degree of attention in financial econometrics and related fields. These models are able to represent some of the stylized features of financial returns, such us uncorrelation in levels but strong dependence in squares and log-squares and leverage effect. Estimation of these models may be carried out by maximum likelihood and Whittle methods. This paper compares the finite sample behaviour of both methods, confirming that maximum likelihood is more efficient but bivariate Whittle sometimes performs comparably