BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AMSE//Event Calendar//FR
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:event-8397@www.amse-aixmarseille.fr
DTSTAMP:20260403T235304Z
CREATED:20260403T235304Z
LAST-MODIFIED:20260403T235304Z
STATUS:CONFIRMED
SEQUENCE:0
SUMMARY:big data and econometrics seminar - Rosnel Sessinou
DTSTART:20210928T120000Z
DTEND:20210928T133000Z
DESCRIPTION:The least square estimator can be shown to depend only on a sin
 gle parameter\, the precision matrix. We show that a regularized estimate o
 f the precision matrix can be directly used to obtain the least square solu
 tion even when the number of covariates can be strictly larger than the sam
 ple size. As biases can occur from different choices of the precision matri
 x estimate\, we show how to construct a (nearly) unbiased estimator irrespe
 ctively of the sparsity within the data generating process. We call this es
 timator the Precision Least Squares (PrLS). Assuming stationarity for the c
 ovariates and the error process we show that the PrLS estimator is (i) asym
 ptotically Gaussian\, (ii) automatically free of the usual regularization b
 ias and (iii) control the directional false discovery rate. As an applicati
 on\, we employ the Precision Least Squares to estimate the predictive conne
 ctedness among daily asset returns of 88 global banks. We show that financi
 al crisis corresponds to a collapse of financial linkage in line with finan
 cial theory predictions.\\n\\nContact: Michel Lubrano : michel.lubrano[at]u
 niv-amu.frPierre Michel : pierre.michel[at]univ-amu.fr\n\nPlus d'informati
 ons: https://www.amse-aixmarseille.fr/fr/evenements/rosnel-sessinou-3
LOCATION:Îlot Bernard du Bois - Salle 21\, AMU - AMSE\, 5-9 boulevard Maur
 ice Bourdet\, 13001 Marseille
URL;VALUE=URI:https://www.amse-aixmarseille.fr/fr/evenements/rosnel-sessinou-3
CONTACT:Michel Lubrano : michel.lubrano[at]univ-amu.frPierre Michel :&nbsp\
 ;pierre.michel[at]univ-amu.fr
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR