Nonlinear Parameter Estimation for State-Space ARCH Models with Missing Observations

Resumen

A new mathematical representation, based on a discrete time nonlinear state space formulation, is presented to characterize AutoRegresive Conditional Heteroskedasticity (ARCH) models. A novel parameter estimation procedure for state-space ARCH models with missing observations, based on an Extended Kalman Filter (EKF) approach, is described and successfully evaluated herein. Finally, through a comparison analysis between our proposed estimation method and a Quasi Maximum Likelihood Estimation (QMLE) technique based on different methods of imputation, some numerical results with simulated data, which make evident the effectiveness and relevance of the proposed nonlinear estimation technique are given.

Autores: Ossandón, S., Bahamondes, N.

Journal: Recent Advances in Systems Science and Mathematical Modelling

Journal Volume:

Journal Issue:

Journal Page: 258-263

Tipo de publicación: no_indexada

Fecha de publicación: 2012

Topics: ARCH models, Missing observations, Nonlinear state space model, Nonlinear estimation, Extended Kalman Filter.

DOI:

URL de la publicación: http://www.wseas.us/e-library/conferences/2012/Paris/MATHSYS/MATHSYS-30.pdf