Bulletin of the
Korean Mathematical Society
BKMS

ISSN(Print) 1015-8634 ISSN(Online) 2234-3016

Article

HOME ALL ARTICLES View

Bull. Korean Math. Soc. 2010; 47(5): 889-905

Printed September 1, 2010

https://doi.org/10.4134/BKMS.2010.47.5.889

Copyright © The Korean Mathematical Society.

Consistent and asymptotically normal estimators for periodic bilinear models

Abdelouahab Bibi and Antony Gautier

Universit\'e Mentouri, Universit\'e Lille 3

Abstract

In this paper, a distribution free approach to the parameter estimation of a simple bilinear model with periodic coefficients is presented. The proposed method relies on minimum distance estimator based on the autocovariances of the squared process. Consistency and asymptotic normality of the estimator, as well as hypotheses testing, are derived. Numerical experiments on simulated data sets are presented to highlight the theoretical results.

Keywords: bilinear time series, periodic coefficients, minimum distance estimator, asymptotic normality, hypotheses testing

MSC numbers: 62M10, 91B84