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:Cambridge Analysts' Knowledge Exchange
SUMMARY:Introduction to Bayesian contraction rates - Kweku
Abraham (University of Cambridge)
DTSTART;TZID=Europe/London:20170510T163000
DTEND;TZID=Europe/London:20170510T173000
UID:TALK72588AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/72588
DESCRIPTION:Statisticians divide into two broad schools: *freq
uentists*\, who assume there is a fixed but unknow
n process governing observed data\, and *Bayesians
*\, for whom statistics is about modelling our bel
iefs and updating sensibly when we see data. The B
ayesian methodology has many attractive properties
\, for example that essentially the same method is
used in any possible set-up. But one can ask how
well this method works if there is indeed a fixed
process governing the data\; this is the goal of *
frequentist analysis of Bayesian procedures*. I wi
ll provide a gentle introduction to this field\, w
ith reference made throughout to the specific prob
lem I'm researching\, that of finding posterior co
ntraction rates (i.e. how fast a Bayesian's belief
s converge to the truth) for estimation in stochas
tic diffusion models.
LOCATION:MR14\, Centre for Mathematical Sciences
CONTACT:Nicolai Baldin
END:VEVENT
END:VCALENDAR