BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Challenges in the Design and Analysis of a Randomized\, Phased Imp
 lementation (Stepped-Wedge) Study in Brazil - Moulton\, L (Johns Hopkins)
DTSTART:20110817T104500Z
DTEND:20110817T113000Z
UID:TALK32389@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:The cluster randomized one-way crossover design\, known as a s
 tepped-wedge design\, is becoming increasingly popular\, especially for he
 alth studies in less industrialized countries. This design\, however\, pre
 sents numerous challenges\, both for design and analysis.\n\nTwo issues re
 garding the design of a stepped-wedge study will be highlighted: randomiza
 tion and power.  Specifically\, first\, there is the question of how best 
 to constrain the randomization so that it is balanced over time with respe
 ct to covariates-a highly constrained but ad hoc procedure will be present
 ed.  Second\, the various pieces of information necessary for a full power
  calculation will be delineated. \n\nAs with cluster-randomized designs in
  general\, close attention must be given to study hypotheses of interest\,
  and the relation of these to the two levels of intervention-cluster and i
 ndividual.  A study of isoniazid prophylaxis implementation in 29 clinics 
 in Rio de Janeiro is used to exemplify the range of questions that can ari
 se.  A few analyses of the data are also presented\, so as to illustrate t
 he degree to which data analytic choices to address these questions can va
 ry the results\, and to show the longitudinal complexities that need be co
 nsidered.\n
LOCATION:Seminar Room 2\, Newton Institute Gatehouse
END:VEVENT
END:VCALENDAR