We will introduce a Monte Carlo type inference in the framework of Markov Switching models to analyse financial time series, namely the Gibbs Sampling. In particular we generalize the results obtained in Albert and Chib (1993), Di Persio and Vettori (2014) and Kim and Nelson (1999) to take into account the switching mean as well as the switching variance case. In particular the volatility of the relevant time series will be treated as a state variable in order to describe the abrupt changes in the behaviour of financial time series which can be implied, e.g., by social, political or economic factors. The accuracy of the proposed analysis will be tested considering financial dataset related to the U.S. stock market in the period 2007–2014.

Gibbs sampling approach to regime switching analysis of financial time series

Di Persio, Luca
;
Frigo, Matteo
2016-01-01

Abstract

We will introduce a Monte Carlo type inference in the framework of Markov Switching models to analyse financial time series, namely the Gibbs Sampling. In particular we generalize the results obtained in Albert and Chib (1993), Di Persio and Vettori (2014) and Kim and Nelson (1999) to take into account the switching mean as well as the switching variance case. In particular the volatility of the relevant time series will be treated as a state variable in order to describe the abrupt changes in the behaviour of financial time series which can be implied, e.g., by social, political or economic factors. The accuracy of the proposed analysis will be tested considering financial dataset related to the U.S. stock market in the period 2007–2014.
2016
State-space system , Bayesian analysis , Markov switching , Maximum likelihood , Regime switching , Gibbs sampling
File in questo prodotto:
File Dimensione Formato  
Gibbs Sampling approach to Regime Switching analysis of financial time series Di Persio Frigo.pdf

accesso aperto

Descrizione: This is the pre (editor) print version of the work. The final version, namely the one published in JCAM, differs just for some small typos.
Tipologia: Documento in Pre-print
Licenza: Dominio pubblico
Dimensione 364.47 kB
Formato Adobe PDF
364.47 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/933509
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 11
social impact