BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An adaptive optimal design with a small fixed stage-one sample siz
 e - Flournoy\, N (University of Missouri-Columbia)
DTSTART:20150706T123000Z
DTEND:20150706T131500Z
UID:TALK60047@talks.cam.ac.uk
CONTACT:42080
DESCRIPTION:A large number of experiments in clinical trials\, biology\, b
 iochemistry\, etc. are\, out of necessity\, conducted in two stages. A fir
 st-stage experiment (a pilot study) is often used to gain information abou
 t feasibility of the experiment or to provide preliminary data for grant a
 pplications. We study the theoretical statistical implications of using a 
 small sample of data (1) to design the second stage experiment and (2) in 
 combination with the second-stage data for data analysis. To illuminate th
 e issues\, we consider an experiment under a non-linear regression model w
 ith normal errors. We show how the dependency between data in the differen
 t stages affects the distribution of parameter estimates when the first-st
 age sample size is fixed and finite\; letting the second stage sample size
  go to infinity\, maximum likelihood estimates are found to have a mixed n
 ormal distribution.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR