BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Network Models with Dynamic Vertex Sets - Simon Lu
nagomez (University College London)
DTSTART;TZID=Europe/London:20160726T100000
DTEND;TZID=Europe/London:20160726T103000
UID:TALK66848AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/66848
DESCRIPTION:Many models of dynamic network data assume t
hat the set of nodes (social actors) remains const
ant over time. By contrast\, we propose a framewor
k that allows for models where both the set of nod
es and the social ties connecting them change over
time. \; We depart from the conventional setu
p where the distribution of the vertex set is a po
int mass\, and instead model its evolution via a s
tochastic process. \; Our approach is modular\
, in the sense that joint distribution of the vert
ex sets over time can be modeled marginally and th
en the joint distribution of the edge sets can be
specified\, conditionally upon it. The conditional
independence statements implied by our approach t
hen mean that posterior sampling for the parameter
s corresponding to these factors (joint distributi
on of the vertex sets\, joint distribution of the
edge sets) can be performed separately. We illustr
ate our methodology via both simulation studies an
d data analysis. \;
Joint work with Sofia
Olhede and Patrick Wolfe.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR