BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://calendrier.umontreal.ca/
X-WR-TIMEZONE:America/Montreal
BEGIN:VEVENT
UID:5da855e1e6249
DTSTAMP:20191017T075201
DTSTART:20170907T153000
SEQUENCE:0
TRANSP:OPAQUE
DTEND:20170907T153000
URL:https://calendrier.umontreal.ca/detail/780351-can-we-identify-a-max-lin
ear-model-on-a-directed-acyclic-graph-by-the-tail-correlation-matrix
LOCATION:Université McGill – Burnside Hall\, 805\, rue Sherbrooke Ouest\
, Montréal\, QC\, Canada\, H3A 0B9
SUMMARY:Can we identify a max-linear model on a directed acyclic graph by t
he tail correlation matrix?
DESCRIPTION:We investigate multivariate regularly varying random vectors wi
th discrete spectral measure induced by a directed acyclic graph (DAG). Th
e tail dependence coefficient measures extreme dependence between two vect
or components\, and we investigate how the matrix of tail dependence coeff
icients can be used to identify the full dependence structure of the rando
m vector on a DAG or even the DAG itself. Furthermore\, we estimate the di
stributional model by the matrix of empirical tail dependence coefficients
. From these observations we want to infer the causal dependence structure
in the data. This is joint work with Nadine Gissibl and Moritz Otto.
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Montreal
X-LIC-LOCATION:America/Montreal
END:VTIMEZONE
END:VCALENDAR