Estimation and filtering of nonlinear MS-DSGE models

Sergey Ivashchenko

HSE Working papers from National Research University Higher School of Economics

Abstract: This article suggests and compares the properties of some nonlinear Markov-switching filters. Two of them are sigma point filters: the Markov switching central difference Kalman filter (MSCDKF) and MSCDKFA. Two of them are Gaussian assumed filters: Markov switching quadratic Kalman filter (MSQKF) and MSQKFA. A small scale financial MS-DSGE model is used for tests. MSQKF greatly outperforms other filters in terms of computational costs. It also is the first or the second best according to most tests of filtering quality (including the quality of quasi-maximum likelihood estimation with use of a filter, RMSE and LPS of unobserved variables).

Keywords: regime switching; second-order approximation; non-linear MS-DSGE estimation; MSQKF; MSCDKF (search for similar items in EconPapers)
JEL-codes: C13 C32 E32 (search for similar items in EconPapers)
Pages: 23 pages
Date: 2016
New Economics Papers: this item is included in nep-dge, nep-ecm, nep-ets, nep-mac and nep-ore
References: Add references at CitEc
Citations: View citations in EconPapers (6)

Published in WP BRP Series: Economics / EC, May 2016, pages 1-23

Downloads: (external link)
https://www.hse.ru/data/2016/05/19/1131872243/136EC2016.pdf (application/pdf)

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:hig:wpaper:136/ec/2016

Access Statistics for this paper

More papers in HSE Working papers from National Research University Higher School of Economics
Bibliographic data for series maintained by Shamil Abdulaev () and Shamil Abdulaev ().