Home > Research > Publications & Outputs > M-Estimation in GARCH Models in the Absence of ...

Electronic data

  • Hallin_Liu_Mukherjee_Springer

    Rights statement: 24m

    Accepted author manuscript, 541 KB, PDF document

    Embargo ends: 1/06/25

    Available under license: Other


View graph of relations

M-Estimation in GARCH Models in the Absence of Higher-Order Moments

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNChapter

Publication date1/06/2023
Host publicationResearch papers in Statistical Inference for Time Series and Related Models: Essays in Honor of Masanobu Taniguchi
Place of PublicationSingapore
Number of pages25
ISBN (Print)9789819908028
<mark>Original language</mark>English


We consider a class of M-estimators of the parameters of a GARCH(p,q) model. These estimators are asymptotically normal, depending on score functions, under milder moment assumptions than the usual quasi maximum likelihood, which makes them more reliable in the presence of heavy tails. We also consider weighted bootstrap approximations of the distributions of these M-estimators and establish their validity. Through extensive simulations, we demonstrate the robustness of these M-estimators under heavy tails and conduct a comparative study of the performance (biases and mean squared errors) of various score functions and the accuracy (confidence interval coverage probabilities) of their bootstrap approximations. In addition to the GARCH(1,1) model, our simulations also involve higher-order models such as GARCH(2,1) and GARCH(1,2) which so far have received relatively little attention in the literature. We also consider the case of order-misspecified models. Finally, we analyze two real financial time series datasets by fitting GARCH(1,1) or GARCH(2,1) models with our M-estimators.