Il giorno 22 novembre, alle ore 14.30, in Aula C del Dipartimento di Matematica dell'Università degli Studi di Milano (via Saldini, 50)
il prof. Matteo Barigozzi (London School of Economics, Londra)
terrà un seminario dal titolo
"Statistical analysis of high-dimensional time series via factor models"
Abstract
High-dimensional time series are among the most common type of dataset available today, and have entered current practice in many areas, including meteorology, genomics, chemometrics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as well as from a numerical point of view. Some of the most successful procedures so far have been based on dimension reduction techniques and, more particularly, on high-dimensional factor models which have been developed, essentially, within time series econometrics.
In this talk I will first review the main results on the representation of high-dimensional stationary times series as generalized dynamic factor models. Then I will present two different estimation techniques based on principal component analysis and on Kalman filtering. Both a time and a frequency domain approach are considered. Last, some extensions to non-stationary time series are also discussed.
Tutti gli interessati sono invitati a partecipare
------------------------------------------- Carati Andrea, Dipartimento di Matematica, Via Saldini 50, 20133 Milano, Italy ------------------------------------------- tel: ++39/02/5835.6139 fax: ++39/02/5835.6090 -------------------------------------------