Improved Estimation in Linear Dynamic Regression Model
Article
Article Title | Improved Estimation in Linear Dynamic Regression Model |
---|---|
ERA Journal ID | 32342 |
Article Category | Article |
Authors | Hoque, Zahirul and Gerlach, Richard |
Journal Title | Journal of Applied Statistical Science |
Journal Citation | 17 (2), pp. 309-314 |
Number of Pages | 6 |
Year | 2005 |
ISSN | 1067-5817 |
Abstract | This paper studies the preliminary test and shrinkage estimators of linear state space regression model via Kalman filtering. The performance of the estimators, with respect to mean square error, has been investigated. It has been revealed that under certain conditions both preliminary test and shrinkage estimators outperform Kalman filter but shrinkage estimator is superior to preliminary test estimator. Hence, the result presented in this paper invalidates the minimum mean square error property of Kalman filter that is widely used by the engineers for estimation of the parameters of linear state space models. |
Keywords | Dynamic model; Kalman filter; preliminary test estimator; shrinkage estimator; mean square error |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 490509. Statistical theory |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | University of Newcastle |
https://research.usq.edu.au/item/z3v01/improved-estimation-in-linear-dynamic-regression-model
22
total views0
total downloads2
views this month0
downloads this month