BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Some Issues Response-Adaptive Designs for Dose-finding Experiments
  - Flournoy\, N (Missouri)
DTSTART:20110819T130000Z
DTEND:20110819T134500Z
UID:TALK32415@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:We discuss some of the many issues involved in selecting an ad
 aptive design.  Included in these considerations are choices to go with fr
 equentist or Bayesian\, parametric or nonparametric procedures.  There is 
 great appeal in using all the information gained to date\, but in many set
 tings\, two or three stage designs have been shown to perform almost as we
 ll as fully adaptive ones.  Furthermore\, with many procedures\, an unfort
 unate string of early responses can have strong undesirable effects on est
 imates.  These consequences can be mitigated by using a short term memory 
 procedure rather than a long term memory procedure.  When interest is in t
 he MTD\, placing subjects around the MTD is symbiotic with efficiently est
 imating the MTD\; this is not so when interest is in finding a dose that i
 s efficacious without toxicity.   The compromise between designing to opti
 mize for ethical treatment versus optimizing for efficiency in estimating 
 best dose should be given serious attention in practice\; although it has 
 been stated that adaptive designs let one do both\, this simply is not the
  case.  Finally\, we briefly consider issues related to stopping for toxic
 ity and lack of efficacy\, sample size recalculation and dropping or addin
 g treatments.  How flexible should a clinical trial be?  Are analysts prep
 ared for the negative impact such flexibility has on estimates of effect s
 ize?\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR