BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling the association between patient characteristics and the 
 change over time in a disease measure using observational cohort data - An
 drew Copas\, Centre for sexual health &amp\; HIV research\, UCL
DTSTART:20100119T143000Z
DTEND:20100119T153000Z
UID:TALK21770@talks.cam.ac.uk
CONTACT:Michael Sweeting
DESCRIPTION:L. Harrison\, D. T. Dunn\, H. Green and A. J. Copas\nHub for T
 rials Methodology Research\, MRC Clinical Trials Unit\, London\n\nIn obser
 vational cohort studies we may wish to examine the associations between th
 e fixed patient\ncharacteristics and the longitudinal changes from baselin
 e in a repeated outcome measure. Many biological\nand other outcome measur
 es are known to be subject to measurement error and biological variation.\
 nIn an initial analysis we may fit a regression model to all outcome measu
 rements\, accounting for all\nthe identified sources of variability\, and 
 see how the characteristics are linked to the change for typical\npatients
 . However\, the characteristics may also be linked to different distributi
 ons of the underlying\noutcome value at baseline\, which itself may be cor
 related with the change over time. Therefore\, if we\nwish to examine the 
 change over time for patients of different characteristics but with the sa
 me underlying\nbaseline value then the initial approach is confounded by t
 he baseline values. Furthermore\, if we attempt\nto remove this confoundin
 g by including the observed baseline measure as a covariate in a model for
 \nlater measurements\, then this may provide an approximate solution but i
 s likely to introduce some bias.\nWe propose a method based on first follo
 wing the initial approach but then\, applying a correction to the\nparamet
 er estimates. This allows the predicted trajectories to be plotted and val
 id significance tests of\nassociation with characteristics. Our approach i
 s compared with other methods and illustrated through a\nsimulation study 
 and an analysis of the association between HIV-1 subtype and immunological
  response\nafter starting antiretroviral therapy.\n
LOCATION:Large Seminar Room\, 1st Floor\, Institute of Public Health\, Uni
 versity Forvie Site\, Robinson Way\, Cambridge
END:VEVENT
END:VCALENDAR