Asymptotic quasi-likelihood based on kernel smoothing for nonlinear and non-gaussian state-space models

Authors

Raed Alzghool
Yan-Xia Lin, University of WollongongFollow

RIS ID

19803

Publication Details

Alzghool, R. & Lin, Y. (2007). Asymptotic quasi-likelihood based on kernel smoothing for nonlinear and non-gaussian state-space models. The 2007 International Conference of Computational Statistics and Data Engineering. World Congress on Engineering (pp. 926-932). London: Newswood Limited, International Association of Engineers.

Abstract

This paper considers parameter estimation for nonlinear and non-Gaussian state-space models with correlation. We propose an asymptotic quasi-likelihood (AQL) approach which utilises a nonparametric kernel estimator of the conditional variance covariances matrix Σ_t to replace the true Σ_t in the standard quasi-likelihood. The kernel estimation avoids the risk of potential miss-specification of Σ_t and thus make the parameter estimator more robust. This has been further verified by empirical studies carried out in this paper.

Link to publisher version (URL)

Routledge