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:MRC Biostatistics Unit Seminars
SUMMARY:Modelling health scores with the multivariate skew
  normal - Jane Hutton\, Department of Statistics\,
  University of Warwick
DTSTART;TZID=Europe/London:20100622T143000
DTEND;TZID=Europe/London:20100622T153000
UID:TALK23489AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/23489
DESCRIPTION:Health care interventions which use quality of lif
 e or health scores often\nprovide data which are s
 kewed and bounded. The scores are typically formed
 \nby adding up responses to a number of questions.
  Different questions might\nhave different weights
 \, but the score will be bounded\, and might be sc
 aled\nto the range 0 to 100. If improvement in hea
 lth over time is measured\,\nscores will tend to c
 luster near the 'healthy' or 'good' boundary as ti
 me\nprogresses\, leading to a skew distribution.  
 Further\, some patients will\ndrop out as time pro
 gresses\, so the scores reflect a selected populat
 ion.\n\nWe fit multivariate skew normal distributi
 ons to data from a randomised\ncontrolled trial of
  four treatments for sprained ankles\, in which sc
 ores\nwere recorded at baseline and 1\, 3 and 9 mo
 nths. In these data\, the scores\nat 3 and 9 month
 s have skew marginal distributions\, but the varia
 nce is\nsimilar across the four times points. We c
 onsider the extent to which\nvariance and skewness
  can be explained by covariates including treatmen
 t\nand age. In order to address the effect of clus
 tering at the boundary\, we\nconsider censored mul
 tivariate normal and skew model. The extended skew
 \nnormal is used to model the selection due to dro
 p-out.
LOCATION:Large Seminar Room\, 1st Floor\, Institute of Publ
 ic Health\, University Forvie Site\, Robinson Way\
 , Cambridge
CONTACT:Michael Sweeting
END:VEVENT
END:VCALENDAR