Statistical Inference for Stochastic Processes

, Volume 3, Issue 1, pp 113–128

Semiparametric Estimation of the Intensity of Long Memory in Conditional Heteroskedasticity

  • Liudas Giraitis
  • Piotr Kokoszka
  • Remigijus Leipus
  • Gilles Teyssière

DOI: 10.1023/A:1009951213271

Cite this article as:
Giraitis, L., Kokoszka, P., Leipus, R. et al. Statistical Inference for Stochastic Processes (2000) 3: 113. doi:10.1023/A:1009951213271


The paper is concerned with the estimation of the long memory parameter in a conditionally heteroskedastic model proposed by Giraitis et al. (1999b). We consider estimation methods based on the partial sums of the squared observations, which are similar in spirit to the classical R / S analysis, as well as spectral domain approximate maximum likelihood estimators. We review relevant theoretical results and present an empirical simulation study.

long memory ARCH models semiparametric estimation modified R / S KPSS and V / S statistics periodogram 

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Liudas Giraitis
    • 1
  • Piotr Kokoszka
    • 2
  • Remigijus Leipus
    • 3
  • Gilles Teyssière
    • 4
  1. 1.Department of EconomicsLondon School of EconomicsLondonUnited Kingdom
  2. 2.Department of Mathematical SciencesUniversity of LiverpoolLiverpoolUnited Kingdom
  3. 3.Department of Mathematics and InformaticsVilnius UniversityVilniusLithuania
  4. 4.European Commission, and GREQAM Joint Research Centre, ISISIspra (VA)Italy

Personalised recommendations