首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Assessing One-Step-Ahead Prediction Error Based on the Median for First-Order Autoregressive Models in the Presence Of Outliers
Authors:Jiin-Huarng Guo  Lynne Billard
Institution:1. Department of Applied Mathematics , National Pingtung University of Education , Pingtung , Taiwan , Republic of China jhguo@mail.npue.edu.tw;3. Department of Statistics , University of Georgia , Athens , Georgia , USA
Abstract:The prediction of the one-step-ahead observation of the first-order autoregressive process in the presence of outliers is considered. The mean square of the prediction error is obtained based on the median estimator of the model parameter for a stationary process. Monte Carlo simulation methods are employed to investigate the performance of the proposed estimator as well as the conventional ordinary least squares estimators proposed by Zhang and Shaman (1995 Zhang , P. , Shaman , P. ( 1995 ). Assessing prediction error in autoregressive models . Trans. Amer. Mathemat. Soc. 347 : 627637 .Crossref], Web of Science ®] Google Scholar]) and Kabaila and He (1999 Kabaila , P. , He , Z. ( 1999 ). On assessing prediction error in autoregressive models . J. Time Ser. Anal. 20 : 663670 .Crossref] Google Scholar]) for a process without outliers. The results show that the proposed method outperforms the conventional method. These conclusions are substantiated with results from actual datasets.
Keywords:Conditional prediction error  Mean square error  Monte Carlo simulation
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号