New Estimator for an Unknown Mean Gaussian AR(1) Process with Additive Outliers
Wararit Panichkitkosolkul* Author for corresponding; e-mail address: wararit@mathstat.sci.tu.ac.th
Volume: Vol.37 No.1 (JANUARY 2010)
Research Article
DOI:
Received: 14 June 2009, Revised: -, Accepted: 9 September 2009, Published: -
Citation: Panichkitkosolkul W., New Estimator for an Unknown Mean Gaussian AR(1) Process with Additive Outliers, Chiang Mai Journal of Science, 2010; 37(1): 14-20.
Abstract
This paper presents a new estimator for an unknown mean Gaussian AR(1) process with additive outliers. We apply the recursive median adjustment to the weighted symmetric estimator of Park and Fuller [1]. The mean square error (MSE) is derived. Simulation is used to investigate the behavior of this new estimator (ρ^RMD-W) compared to the weighted symmetric estimator (ρ^W) and the recursively mean adjusted weighted symmetric estimator (ρ^R-W) proposed by Niwitpong [2]. Simulation results have shown that the proposed estimator, ρ^RMD-W , provides a MSE lower than those of ρ^W and ρ^R-W for almost all situations.