BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:3973a012724d3a4fa2884e8c93877fda
CATEGORIES:Seminars
CREATED:20190114T122915
SUMMARY:Alessandra Luati - Università di Bologna
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:<p><strong><span style="font-size: 11pt; font-family: 'Calibri','sans-serif
 ';">Spectral Models for Locally Stationary Processes</span></strong><span s
 tyle="font-size: 11pt; font-family: 'Calibri','sans-serif';"> (Joint with T
 ommaso Proietti and Stefano Grassi)</span></p><p><span style="font-size: 11
 pt; font-family: 'Calibri','sans-serif';">Abstract: </span></p><p style="te
 xt-align: justify;">A class of models for the time-varying spectrum of a lo
 cally stationary process is introduced. The models are specified in the fre
 quency domain and the class depends on a power parameter that applies to th
 e spectrum so that it can be locally represented by a finite Fourier polyno
 mial. The coefficients of the polynomial have an interpretation as generali
 zed autocovariances whose smooth time variation is determined according to 
 a linear combination of logistic transition functions of the time index. Es
 timation is carried out in the frequency domain based on the generalized Wh
 ittle likelihood. Parametric inference is developed.</p><p><span style="fon
 t-size: 11pt; font-family: 'Calibri','sans-serif';"></span></p>
DTSTAMP:20260426T200339Z
DTSTART:20190404T163000Z
DTEND:20190404T180000Z
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR