BEGIN:VCALENDAR
PRODID:-//SiteBuilder 2//University of Warwick ITS Web Team//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-TIMEZONE:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:VTIMEZONE
TZID:Europe/London
LAST-MODIFIED:20201010T011803Z
TZURL:http://tzurl.org/zoneinfo/Europe/London
X-LIC-LOCATION:Europe/London
X-PROLEPTIC-TZNAME:LMT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+000115
TZOFFSETTO:+0000
DTSTART:18471201T000000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19160521T020000
RDATE:19170408T020000
RDATE:19180324T020000
RDATE:19190330T020000
RDATE:19200328T020000
RDATE:19210403T020000
RDATE:19220326T020000
RDATE:19230422T020000
RDATE:19240413T020000
RDATE:19270410T020000
RDATE:19300413T020000
RDATE:19330409T020000
RDATE:19340422T020000
RDATE:19350414T020000
RDATE:19380410T020000
RDATE:19390416T020000
RDATE:19400225T020000
RDATE:19460414T020000
RDATE:19470316T020000
RDATE:19480314T020000
RDATE:19490403T020000
RDATE:19530419T020000
RDATE:19540411T020000
RDATE:19570414T020000
RDATE:19600410T020000
RDATE:19680218T020000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19161001T030000
RDATE:19170917T030000
RDATE:19180930T030000
RDATE:19190929T030000
RDATE:19201025T030000
RDATE:19211003T030000
RDATE:19221008T030000
RDATE:19391119T030000
RDATE:19471102T030000
RDATE:19481031T030000
RDATE:19491030T030000
RDATE:19711031T030000
END:STANDARD
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19230916T030000
RRULE:FREQ=YEARLY;UNTIL=19240921T020000Z;BYMONTH=9;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19250419T020000
RRULE:FREQ=YEARLY;UNTIL=19260418T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19251004T030000
RRULE:FREQ=YEARLY;UNTIL=19381002T020000Z;BYMONTH=10;BYMONTHDAY=2,3,4,5,6,
 7,8;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19280422T020000
RRULE:FREQ=YEARLY;UNTIL=19290421T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19310419T020000
RRULE:FREQ=YEARLY;UNTIL=19320417T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19360419T020000
RRULE:FREQ=YEARLY;UNTIL=19370418T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BDST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19410504T020000
RDATE:19450402T020000
RDATE:19470413T020000
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19410810T030000
RRULE:FREQ=YEARLY;UNTIL=19430815T010000Z;BYMONTH=8;BYMONTHDAY=9,10,11,12,
 13,14,15;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BDST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19420405T020000
RRULE:FREQ=YEARLY;UNTIL=19440402T010000Z;BYMONTH=4;BYMONTHDAY=2,3,4,5,6,7
 ,8;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19440917T030000
RDATE:19450715T030000
RDATE:19470810T030000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19451007T030000
RRULE:FREQ=YEARLY;UNTIL=19461006T020000Z;BYMONTH=10;BYMONTHDAY=2,3,4,5,6,
 7,8;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19500416T020000
RRULE:FREQ=YEARLY;UNTIL=19520420T020000Z;BYMONTH=4;BYMONTHDAY=14,15,16,17
 ,18,19,20;BYDAY=SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19501022T030000
RRULE:FREQ=YEARLY;UNTIL=19521026T020000Z;BYMONTH=10;BYMONTHDAY=21,22,23,2
 4,25,26,27;BYDAY=SU
END:STANDARD
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19531004T030000
RRULE:FREQ=YEARLY;UNTIL=19601002T020000Z;BYMONTH=10;BYMONTHDAY=2,3,4,5,6,
 7,8;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19550417T020000
RRULE:FREQ=YEARLY;UNTIL=19560422T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19580420T020000
RRULE:FREQ=YEARLY;UNTIL=19590419T020000Z;BYMONTH=4;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19610326T020000
RRULE:FREQ=YEARLY;UNTIL=19630331T020000Z;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19611029T030000
RRULE:FREQ=YEARLY;UNTIL=19671029T020000Z;BYMONTH=10;BYMONTHDAY=23,24,25,2
 6,27,28,29;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19640322T020000
RRULE:FREQ=YEARLY;UNTIL=19670319T020000Z;BYMONTH=3;BYMONTHDAY=19,20,21,22
 ,23,24,25;BYDAY=SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:BST
TZOFFSETFROM:+0100
TZOFFSETTO:+0100
DTSTART:19681026T230000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19720319T020000
RRULE:FREQ=YEARLY;UNTIL=19800316T020000Z;BYMONTH=3;BYMONTHDAY=16,17,18,19
 ,20,21,22;BYDAY=SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19721029T030000
RRULE:FREQ=YEARLY;UNTIL=19801026T020000Z;BYMONTH=10;BYMONTHDAY=23,24,25,2
 6,27,28,29;BYDAY=SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19810329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19811025T020000
RRULE:FREQ=YEARLY;UNTIL=19891029T010000Z;BYMONTH=10;BYMONTHDAY=23,24,25,2
 6,27,28,29;BYDAY=SU
END:STANDARD
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19901028T020000
RRULE:FREQ=YEARLY;UNTIL=19951022T010000Z;BYMONTH=10;BYDAY=4SU
END:STANDARD
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
DTSTART:19960101T000000
END:STANDARD
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19961027T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260308T033128Z
DTSTART;VALUE=DATE-TIME:20160212T140000
DTEND;VALUE=DATE-TIME:20160212T163000
SUMMARY:OxWaSP Seminar
TZID:Europe/London
UID:20160212-094d43454f5f8210014fa771c21f6825@warwick.ac.uk
CREATED:20150907T105454Z
DESCRIPTION:David Rossell (University of Warwick) The model separation pr
 inciple for Bayesian model choice Abstract: Given a collection of candid
 ate probability models for an observed data y\, a fundamental statistica
 l task is to evaluate which models are more likely to have generated y. 
 Tackling this problem within a Bayesian framework requires one to comple
 ment the probability model for y (likelihood) with a prior probability m
 odel on the parameters (which could be infinitely-dimensional) describin
 g each of the candidate models\, as well as to specify model prior proba
 bilities and possibly a utility function. The model separation principle
  states that the models under consideration should be minimally differen
 t from each other\, else it becomes hard for us to distinguish them on t
 he bases of the observed y. In the common setting where some of the mode
 ls are nested this principle is violated\, as say Model 1 is a particula
 r case of Model 2 and thus these models are not well separated. We shall
  review a class of prior distributions called non-local priors (NLPs) as
  a way to enforce the model separation principle and some of the NLP pro
 perties\, focusing on parsimony and accelerated convergence rates in hig
 h-dimensional inference. We shall illustrate their use in ongoing work r
 elated to regression\, robust regression and mixture models. Darren Wilk
 inson (Newcastle University) Bayesian inference for partially observed M
 arkov processes Abstract: A number of interesting statistical applicatio
 ns require the estimation of parameters underlying a nonlinear multivari
 ate continuous time Markov process model\, using partial and noisy discr
 ete time observations of the system state. Bayesian inference for this p
 roblem is difficult due to the fact that the discrete time transition de
 nsity of the Markov process is typically intractable and computationally
  intensive to approximate. Nevertheless\, it is possible to develop part
 icle MCMC algorithms which are exact\, provided that one can simulate ex
 act realisations of the process forwards in time. Such algorithms\, ofte
 n termed "likelihood free" or "plug-and-play" are very attractive\, as t
 hey allow separation of the problem of model development and simulation 
 implementation from the development of inferential algorithms. Such tech
 niques break down in the case of perfect observation or high-dimensional
  data\, but more efficient algorithms can be developed if one is prepare
 d to deviate from the likelihood free paradigm\, at least in the case of
  diffusion processes. The methods will be illustrated using examples fro
 m population dynamics and stochastic biochemical network dynamics. 14.00
  - 15.00: David Rossell\, “The model separation principle for Bayesian m
 odel choice.” 15.00 - 15.30: Coffee break 15.30 - 16.30: Darren Wilkinso
 n\, “Bayesian inference for partially observed Markov processes.”
LOCATION:B2.02 (Sci Conc)
CATEGORIES:Seminars
LAST-MODIFIED:20160211T114624Z
ORGANIZER;CN=Paula Matthews:
END:VEVENT
END:VCALENDAR