Venerdì 9 maggio, alle ore 14.30 presso il Dipartimento di Statistica,
il Prof. PETROS DELLAPORTAS, Department of Statistics of Athens Economic University
terra' un seminario su
CONTEMPORANEOUS ARMA STRUCTURES FOR TIME- VARYING COVARIANCES WITH APPLICATIONS
TO
QUANTITATIVE FINANCE
Abstract:
We use ARMA structures to model contemporaneous correlations amongst
very many time
series. The ensuing method is related to and compares favorably with
the (dynamic) factor
models, multivariate GARCH and stochastic volatility models developed
in the last decade in
the area of quantitative finance. As in factor models, the method has
the drawback of producing
results that are unique up to an orthogonal rotation (permutation of
the variables in a vector
of responses). However, it has the added advantage that the parameters
are meaningful and
interpretable as the coefficients of the observables and their innovations
rather than as the factor
loadings of some latent factors. The key theoretical tool used is the
modified Cholesky decompo-
sition of a covariance matrix rather than its traditional spectral
decomposition. Regressogram
of the components of the modified Cholesky decomposition is used, in
a manner similar to the
correlogram in time series, to identify parsimonious models for the
large number of parameters
employing parametric, non-parametric and Bayesian methods.
Si possono trovare ulteriori informazioni all'indirizzo: http://www.dst.unive.it/seminari2003.html
-- Stefano Tonellato Dipartimento di Statistica - Università Ca' Foscari di Venezia Campiello S. Agostin, S. Polo 2347 - 30125 Venezia - ITALY Phone +39-041-2347422 Fax +39-041-710355 E-mail stone@unive.it