BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Regret-regression for optimal dynamic treatment allocation\, witho
 ut and with missing data - Robin Henderson\, Newcastle University
DTSTART:20131129T160000Z
DTEND:20131129T170000Z
UID:TALK47612@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION:A system is monitored over time. At time $t$ an input $A_t$ is
  determined and an output $S_{t+}$ observed.  The input is directly contro
 llable  by an experimenter but the  output $S_{t+}$ is not.\n \nThe statem
 ent above applies to a raft of problems across multiple areas\, including 
 control\, machine learning\, stochastic scheduling and many others. A spec
 ial case of growing interest in the biostatistical literature is the need 
 for statistical  methodology  aimed at determining optimal dynamic treatme
 nt regimes from observational data.  Motivation  is primarily related to i
 ndividualised medicine and causal inference.\n \nBuilding on the  advantag
 e learning approach\,  we propose a modelling and estimation strategy that
  incorporates the regret functions of Murphy (2003) into a regression mode
 l for observed responses. Estimation is quick and diagnostics are availabl
 e\, meaning a variety of candidate models can be compared.  We consider th
 ree issues relating to the  missing data problem that is ubiquitous in pra
 ctical applications: estimation\, sub-optimal decisions and non-recovery. 
 The methods are illustrated using data on patients on long-term anticoagul
 ation treatment.
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR