BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:BSU Seminar: 'Covariate Adjustment in Randomized Experiments with 
 Incomplete Covariate and Outcome Data' - Prof Fan Li\, Duke University 
DTSTART:20230418T130000Z
DTEND:20230418T140000Z
UID:TALK199297@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:When analyzing data from randomized clinical trials\, covariat
 e adjustment can be used to account for chance imbalance in baseline covar
 iates and to increase precision of the treatment effect estimate. A practi
 cal barrier to covariate adjustment is the presence of missing data. In th
 is paper\, in the light of recent theoretical advancement\, we review seve
 ral covariate adjustment methods with incomplete covariate data. We invest
 igate the implications of the missing data mechanism on estimating the ave
 rage treatment effect in randomized clinical trials with continuous or bin
 ary outcomes. We consider settings where the outcome data are fully observ
 ed or are missing at random\; in the latter setting\, we propose a full we
 ighting approach that combines inverse probability weighting for adjusting
  for missing outcomes and overlap weighting for covariate adjustment. We c
 onduct comprehensive simulation studies to examine the finite-sample perfo
 rmance of the proposed methods and compare with a range of common alternat
 ives. We find that conducting the proposed adjustment methods generally im
 proves the precision of treatment effect estimates regardless of the imput
 ation methods when the proportion of missingness is not too large and the 
 adjusted covariate is associated with the outcome. We apply the methods to
  the Childhood Adenotonsillectomy Trial to assess the effect of adenotonsi
 llectomy on neurocognitive functioning scores.
LOCATION:Online seminar. To register to attend\, please click here: https:
 //us02web.zoom.us/meeting/register/tZMoc-yoqj4uHNMIXU5Js9MmiIW6mBtvGGFA
END:VEVENT
END:VCALENDAR