Improvement on additive outlier detection procedure in bilinear model

Document Type

Article

Publication Date

1-1-2008

Abstract

This paper considers the problem of outlier detection in bilinear time series data; with special focus on two most basic models BL(1,0,1,1) and BL(1,1,1,1). The formulation of effect of additive outlier on the observations and residuals has been developed and the least squares estimator of the outlier effect has been derived. Consequently, an outlier detection procedure employing bootstrapping method to estimate the variance of the estimator has been proposed. In this paper, we propose to use the mean absolute deviance and trimmed mean methods to improve the performances of the procedure. Using simulation works, we show that trimmed method has successfully improved the performance. Subsequently the procedure is applied to a real data set.

Keywords

Additive outlier, Bilinear, Bootstrapping, Least squares method, Rainfall data

Divisions

foundation,MathematicalSciences

Publication Title

Malaysian Journal of Science

Volume

27

Issue

2

Publisher

Faculty of Science, University of Malaya

This document is currently not available here.

Share

COinS