A Bayesian MCMC based estimation of Long memory in state space model
(2014) 1st International Work-Conference on Time Series (ITISE) p.1341-1352- Abstract
- To estimate the long memory series in the framework of state space model is rarely documented although the theoretical foundation was well built in late 90s, and the literatures concentrate mainly on the estimation in stationary case. This paper aims to estimate the parameters in a wide range of long memory series by applying approximate Maximum Likelihood Estimation (MLE) and Bayesian Monte Carlo Markov Chain (MCMC) methodology. We show that both methods perform quite well with the exception in the case that the series is nearly non-stationary, where pure MLE gives out seriously over biased estimation and the Bayesian MCMC estimation can avoid this problem when pre-knowledge is available.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7975656
- author
- Li, Yushu LU
- organization
- publishing date
- 2014
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- fractional difference, state space model, Kalman filter, Metropolis-Hastings algorithm
- host publication
- International Work-Conference on Time Series (ITISE 2014)
- pages
- 1341 - 1352
- publisher
- Copicentro Granada SL
- conference name
- 1st International Work-Conference on Time Series (ITISE)
- conference location
- Granada, Spain
- conference dates
- 2014-06-25 - 2014-06-27
- external identifiers
-
- wos:000359136600149
- ISBN
- 9788415814974
- language
- English
- LU publication?
- yes
- id
- 3b63615c-c0aa-4b1d-9d8d-0f353d4de752 (old id 7975656)
- date added to LUP
- 2016-04-04 11:44:02
- date last changed
- 2020-05-08 11:27:23
@inproceedings{3b63615c-c0aa-4b1d-9d8d-0f353d4de752, abstract = {{To estimate the long memory series in the framework of state space model is rarely documented although the theoretical foundation was well built in late 90s, and the literatures concentrate mainly on the estimation in stationary case. This paper aims to estimate the parameters in a wide range of long memory series by applying approximate Maximum Likelihood Estimation (MLE) and Bayesian Monte Carlo Markov Chain (MCMC) methodology. We show that both methods perform quite well with the exception in the case that the series is nearly non-stationary, where pure MLE gives out seriously over biased estimation and the Bayesian MCMC estimation can avoid this problem when pre-knowledge is available.}}, author = {{Li, Yushu}}, booktitle = {{International Work-Conference on Time Series (ITISE 2014)}}, isbn = {{9788415814974}}, keywords = {{fractional difference; state space model; Kalman filter; Metropolis-Hastings algorithm}}, language = {{eng}}, pages = {{1341--1352}}, publisher = {{Copicentro Granada SL}}, title = {{A Bayesian MCMC based estimation of Long memory in state space model}}, year = {{2014}}, }