BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Lecture or Presentation
DESCRIPTION:Research Seminar Speaker: Ben Shaby\, Ph.D.\, Assistant Profess
or\, Department of Statistics and the Institute for CyberScience at Penn St
ate\n\nTitle: \n\nMax-Infinitely Divisible Models for Spatial Extremes Usin
g Random Effects\n\nAbstract:\n\nRare events can have crippling effects on
economies\, infrastructure\, and human health and wellbeing. Their outsized
impacts make extreme events critical to understand\, yet their defining ch
aracteristic\, rareness\, means that precious little information is availab
le to study them. Extremes of environmental processes are inherently spatia
l in structure\, as a given event necessarily occurs over a particular spat
ial extent at a particular collection of locations. Characterizing their pr
obabilistic structure therefore requires moving well beyond the well-unders
tood models that describe marginal extremal behavior at a single location.
Rather\, stochastic process models are needed to describe joint tail event
across space. Distinguishing between the subtly different dependence charac
teristics implied by current families of stochastic process models for spat
ial extremes is difficult or impossible based on exploratory analysis of da
ta that is by definition scarce. Furthermore\, different choices of extrema
l dependence classes have large consequences in the analysis they produce.\
n\nI will present stochastic models for extreme events in space that are 1)
flexible enough to transition across different classes of extremal depende
nce\, and 2) permit inference through likelihood functions that can be comp
uted for large datasets. These modeling goals are accomplished by represent
ing stochastic dependence relationships conditionally\, which will induce d
esirable tail dependence properties and allow efficient inference through M
arkov chain Monte Carlo. I will describe models for spatial extremes using
max-infinitely divisible processes\, a generalization of the limiting max-s
table class of processes which has received a great deal of attention. This
work extends previous family of max-stable models based on a conditional h
ierarchical representation to the more flexible max-id class\, thus accommo
dating a wider variety of extremal dependence characteristics while retaini
ng the structure that makes it computationally attractive.
DTEND:20190415T235000Z
DTSTAMP:20230603T135130Z
DTSTART:20190415T225500Z
GEO:44.56647;-123.279005
LOCATION:Milam Hall\, 213
SEQUENCE:0
SUMMARY:STATISTICS RESEARCH SEMINAR: Dr. Ben Shaby\, Penn State
UID:tag:localist.com\,2008:EventInstance_4520408
URL:https://events.oregonstate.edu/event/statistics_research_seminar_dr_ben
_shaby_penn_state
END:VEVENT
END:VCALENDAR