Bayesian Estimation of Time Series Models with Change Points

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F15%3A43906541" target="_blank" >RIV/62156489:43110/15:43906541 - isvavai.cz</a>

Výsledek na webu

<a href="http://mme2015.zcu.cz/downloads/MME_2015_proceedings.pdf" target="_blank" >http://mme2015.zcu.cz/downloads/MME_2015_proceedings.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Bayesian Estimation of Time Series Models with Change Points

Popis výsledku v původním jazyce

Time series are frequently burdened with externally induced points of change due to political decisions, changed technology or natural causes. Change point model assumes that data were generated by random process depending on the different regimes or states. This paper applies a Bayesian approach to estimation of multiple change point model of time series. It is founded upon a definition of unobserved state variable indicating a regime for sampling the specific observation. It is as-sumed that one or more change-points separate the regimes. Position of the change-points is unknown and must be estimated. Markov Chain Monte Carlo method is chosen to generate samples from conditional distributions of the parameters. Com-parisons of alternative models arepossible with quality indicators utilizing the marginal log likelihood function, primarily the Bayes factor. Diagnostic tools check the mixing properties of the sampled Markov chains required at convergence. 95% Highest Posterior Density

Název v anglickém jazyce

Bayesian Estimation of Time Series Models with Change Points

Popis výsledku anglicky

Time series are frequently burdened with externally induced points of change due to political decisions, changed technology or natural causes. Change point model assumes that data were generated by random process depending on the different regimes or states. This paper applies a Bayesian approach to estimation of multiple change point model of time series. It is founded upon a definition of unobserved state variable indicating a regime for sampling the specific observation. It is as-sumed that one or more change-points separate the regimes. Position of the change-points is unknown and must be estimated. Markov Chain Monte Carlo method is chosen to generate samples from conditional distributions of the parameters. Com-parisons of alternative models arepossible with quality indicators utilizing the marginal log likelihood function, primarily the Bayes factor. Diagnostic tools check the mixing properties of the sampled Markov chains required at convergence. 95% Highest Posterior Density

Druh

D - Stať ve sborníku

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Mathematical Methods in Economics 2015: Conference Proceedings

ISBN

978-80-261-0539-8

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1-6

Název nakladatele

Západočeská univerzita

Místo vydání

Plzeň

Místo konání akce

Cheb

Datum konání akce

9. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—