[Forum SIS] semianrio Prof.ssa A. Mira

[Julia Mortera]

*Nell'ambito della Scuola dottorale in Economia e Metodi Quantitativi*

*Dottorato in Metodi Statistici per l'Economia e l'Impresa*

**

*presso il Dipartimento di Economia, Università Roma Tre si terrà il 
seminario*

**

**

*BAYESIAN SEMIPARAMETRIC MULTIPLICATIVE ERROR MODEL FOR DAILY REALIZED 
VOLATILITY*

**

*Prof.ssa Antonietta Mira*

*Swiss Finance Institute, University of Lugano, Switzerland
and
Dipartimento di Economia, Università dell'Insubria*


**

**

*13 Marzo ore 15.30*

*aula 24 - 3° piano
*


*Abstract*
Co-authors: Reza Solgi, Swiss Finance Institute, University of Lugano, Switzerland



We propose an asymmetric semiparametric Multiplicative Error Model (MEM) for
positive persistent time series. In traditional MEM, the innovations are
typically assumed to be Gamma distributed (with one free parameter that
ensures unit mean of the innovations and identifiability of the model),
however empirical investigations unveil the inappropriateness of this
choice. In the proposed approach, the conditional mean of the time series is
modeled parametrically, while we model its conditional distribution
nonparametrically by Dirichlet process mixture with the Gamma distribution
as its kernel. A Markov Chain Monte Carlo algorithm on the space of a the
parameter expanded (PX) model is designed, based on the projection
of models in the PX-space into the space of identifiable models. An adaptive
MH-within-Gibbs algorithm is proposed to  efficiently sample the model's
parameters. Simulation algorithm and adaptation mechanism have been designed
considering the many-to-one mapping between PX space and original space.
This model is applied to the time series of daily realized volatility of
some indices, and is compared to similar parametric models available. Our
simulations and empirical studies show better predictive performance,
flexibility and robustness to misspecification of our Bayesian
semiparametric model.





-- 
Prof.ssa Julia Mortera
Dipartimento di Economia
Università Roma Tre
Via Silvio D'Amico 77
00145 Roma
Tel: +39 06 57335732
Fax: +39 06 57335771
http://dipeco.uniroma3.it/docenti.asp?id=123#

-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20130312/73e567d0/attachment.html>