Maximum Likelihood Estimation of Regression Effects in State Space Models

Qian Hang ()
Additional contact information
Qian Hang: The MathWorks, Inc., 55 Centre Street, Natick, MA 01760, USA

Journal of Econometric Methods, 2025, vol. 14, issue 1, 13-19

Abstract: Unknown parameters, including regression coefficients, in state space models can be estimated by maximum likelihood. An alternative approach is to augment the state vector to include regression coefficients. However, the state estimator obtained by the Kalman filter is numerically different from the maximum likelihood estimator. We address the discrepancy by a novel method based on proper distributions returned by the ordinary Kalman filter without dependency on diffuse initialization. We prove that maximizing a low-dimensional objective function that combines the likelihood, the filtering mean and variance can reproduce the high-dimensional maximum likelihood results.

Keywords: Bayesian analysis; diffuse prior; posterior distribution; likelihood concentration; 62F10; 62L12; 65Y04 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/jem-2024-0020 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:jecome:v:14:y:2025:i:1:p:13-19:n:1001

Ordering information: This journal article can be ordered from
https://www.degruyte ... journal/key/jem/html

DOI: 10.1515/jem-2024-0020

Access Statistics for this article

Journal of Econometric Methods is currently edited by Tong Li and Zhongjun Qu

More articles in Journal of Econometric Methods from De Gruyter
Bibliographic data for series maintained by Peter Golla ().