Comparison of recursive parameter estimation and non-linear filtration

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F12%3A00060981" target="_blank" >RIV/00216224:14560/12:00060981 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Comparison of recursive parameter estimation and non-linear filtration
Original language description
The contribution compares and contrasts the results of time-varying parameters estimation pursued by two methodologically different approaches, all in the context of a DSGE model. The original results Capek 2011 were obtained by the so-called recursive,rolling and ``first observation'' analysis. The novel methodology uses Unscented Particle Filter to filter trajectories of time-varying parameters. The comparisons are presented on the case of three parameters of a DSGE model, which demonstrate a match in the evolution of the parameter estimates. Recursive impulse response functions are compared on two cases, which also match. Although not all of the results obtained from two different methodologies completely match, the most important parameter changesare similarly captured by both approaches.
Czech name
—
Czech description
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of 30th International Conference Mathematical Methods in Economics
ISBN
9788072487790
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
85-90
Publisher name
Silesian University, School of Business Administration
Place of publication
Karviná
Event location
Karviná
Event date
Sep 11, 2012
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)