[Forum SIS] Politecnico di Milano, seminario J.O. Ramsay
Laura M. Sangalli
laura.sangalli a polimi.it
Ven 9 Set 2011 17:38:40 CEST
Si avvisa che in data 23-09-2011, alle ore 11:30 precise,
presso Aula Seminari F. Saleri VI Piano MOX - Dipartimento di
Matematica, Politecnico di Milano,
nell'ambito delle iniziative MOX e del progetto FIRB Futuro in Ricerca
SNAPFUN, si svolgerà il seguente seminario:
Relatore:
James O. Ramsay,
McGill University, Montreal, Canada
Titolo:
Estimating a Variance-Covariance Surface for Functional Data using
Finite Elements
Abstract:
In functional data analysis, as in its multivariate counterpart,
estimates of the bivariate covariance kernel sigma(s,t) and its inverse
are useful for many things, and we need the inverse of a covariance
matrix or kernel especially often. However, the dimensionality of
functional observations often exceeds the sample size available to
estimate sigma(s,t). Then the analogue of the multivariate sample
estimate is singular and non-invertible. Even when this is not the
case, the high dimensionality of the usual estimate often implies
unacceptable sample variability and loss of degrees of freedom for model
fitting. The common practice of employing low-dimensional principal
component approximations to sigma(s,t) to achieve invertibility also
raises serious issues.
This talk describes a functional and nonsingular estimate of sigma(s,t)
and its inverse defined by an expansion in terms of finite element basis
functions that permits the user to control the resolution of the
estimate as well as the time lag over which covariance may be nonzero.
This estimate also permits the estimation of covariances and
correlations at observed pairs of sampling points, and therefore has
applications to many classical statistical problems, such as discrete
but unequally spaced time and spatial series.
Tutti gli interessati sono invitati a partecipare.
Cordiali saluti,
Laura Sangalli
--
Laura Maria Sangalli
MOX - Dipartimento di Matematica
Politecnico di Milano
Piazza Leonardo da Vinci 32
20133 Milano - Italy
tel: +39 02 2399 4554
fax: +39 02 2399 4606
email: laura.sangalli at polimi.it
url: http://mox.polimi.it/~sangalli
http://mox.polimi.it/~sangalli/firb.html
Maggiori informazioni sulla lista
Sis