Estimation of variance components in dynamic linear models
Two types of recursive estimators are developed for the variance components [sigma]2 and [tau]2 of the dynamic linear model: non-Bayesian and Bayesian. From a frequentist point of view, both types of estimators are mean square consistent. The non-Bayesian estimator of [sigma]2 is also unbiased.
Year of publication: |
1999
|
---|---|
Authors: | Zacks, Shelemyahu ; Wang, Xiaodong |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 41.1999, 3, p. 325-330
|
Publisher: |
Elsevier |
Keywords: | Dynamic linear model Kalman filter Variance components |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Perry, David, (2005)
-
A note on optimal stopping for possible change in the intensity of an ordinary Poisson process
Brown, Marlo, (2006)
-
Statistical problems in the control of multi-echelon inventory systems
Zacks, Shelemyahu, (1981)
- More ...