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:Statistics
SUMMARY:Bayesian regression models for complex spatially o
 r serially correlated functional data - Jeffrey Mo
 rris\, MD Anderson Cancer Center
DTSTART;TZID=Europe/London:20181026T160000
DTEND;TZID=Europe/London:20181026T170000
UID:TALK109654AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/109654
DESCRIPTION:A series of Bayesian regression modeling strategie
 s that can be used for spatially or longitudinally
  correlated functional data will be described. The
  methods are intended for use with complex functio
 nal data\, measured on fine grids and with complex
 ities including multi-dimensional and possibly non
 -Euclidean domains\, local features like changepoi
 nts and peaks\, and sampled on high-dimensional fi
 ne grids.  Intrafunctional correlation is handled 
 through basis function modeling\, while interfunct
 ional correlation is captured by one of three appr
 oaches: (1) parametric or nonparametric random eff
 ect functions\, (2) separable or non-separable spa
 tial (or temporal) inter-functional processes\, or
  (3) tensor-basis function modeling. Rigorous Baye
 sian inference is done in such a way that adjusts 
 for any potential multiple testing issues. We will
  describe these general approaches and illustrate 
 them on a series of complex\, high-dimensional\, s
 patially and longitudinally correlated functional 
 data sets coming from strain tensor data from a gl
 aucoma study\, bladder cancer genomic maps\, event
 -related potential data from a smoking cessation s
 tudy. We will also discuss recent work in which we
  have developed spatiotemporal quantile functional
  regression approaches that we are applying to mod
 el temporal climate change in terms of intraseason
 al temperature and precipitation distributions.  F
 ull Bayesian infererence is available for answerin
 g inferential questions while accounting for multi
 ple testing according to experimentwise error rate
  and/or false discovery rate criteria.  These meth
 ods are encapsulated within the BayesFMM package o
 f general Bayesian functional mixed models\, for w
 hich we are developing general software in R and M
 atlab.
LOCATION:MR12
CONTACT:Dr Sergio Bacallado
END:VEVENT
END:VCALENDAR