BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A cluster-randomised cross-over trial - White\, I (MRC)
DTSTART:20110815T153500Z
DTEND:20110815T161500Z
UID:TALK32352@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:I will describe a trial which combined a cluster-randomised de
 sign with \na cross-over design. The Preterm Infant Parenting (PIP) trial 
 evaluated \na nurse-led training intervention delivered to parents of prem
 aturely \nborn babies to help them meet their babies' needs. An individual
 ly \nrandomised trial risked extensive "contamination" of parents in the \
 ncontrol arm with knowledge of the intervention\, so the investigators \ni
 nstead randomised neonatal units. However\, neonatal units differ \nwidely
 \, and only 6 neonatal units were available\, so a conventional \ncluster 
 randomised design would have been underpowered. In the selected \ndesign\,
  the six neonatal units were randomly allocated to deliver \nintervention 
 or control to families recruited during a first 6-month \nperiod\; after a
  2-month interval\, each unit then delivered the opposite \ncondition to f
 amilies recruited during a second 6-month period.\n\nI will present the re
 lative precisions of individually randomised\, \ncluster-randomised and cl
 uster-crossover designs\, and design issues \nincluding the need for a was
 h-out period to minimise carry-over. The \nanalysis can be conveniently do
 ne using cluster-level summaries. I will \nend by discussing whether clust
 er-crossover designs should be more \nwidely used.\n\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR