Bootstrapping M-estimators in generalized autoregressive conditional heteroscedastic models. (6th May 2020)

• Record Type: Journal Article
• Authors: Mukherjee, K
• Is Part Of: Biometrika. Volume 107:Number 3(2020:Sep.)
• Page Start: 753
• Page End: 760
• Publication Date: 2020-05-06
• Subjects: Generalized autoregressive conditional heteroscedastic model -- M-estimation -- Weighted bootstrap; Biometry -- Periodicals; 570.1519505
• DOI: 10.1093/biomet/asaa023
• Languages: English
• ISSNs: 0006-3444

Abstract

Summary: We consider the weighted bootstrap approximation to the distribution of a class of M-estimators for the parameters of the generalized autoregressive conditional heteroscedastic model. We prove that the bootstrap distribution, given the data, is a consistent estimate in probability of the distribution of the M-estimator, which is asymptotically normal. We propose an algorithm for the computation of M-estimates which at the same time is useful for computing bootstrap replicates from the given data. Our simulation study indicates superior coverage rates for various weighted bootstrap schemes compared with the rates based on the normal approximation and existing bootstrap methods for the generalized autoregressive conditional heteroscedastic model, such as percentile $t$ -subsampling schemes. Since some familiar bootstrap schemes are special cases of the weighted bootstrap, this paper thus provides a unified theory and algorithm for bootstrapping in generalized autoregressive conditional heteroscedastic models.