BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:New Approaches for Inference on Optimal Treatment Regimes - Lan Wa
 ng (University of Miami)
DTSTART:20211105T160000Z
DTEND:20211105T170000Z
UID:TALK162133@talks.cam.ac.uk
CONTACT:Qingyuan Zhao
DESCRIPTION:Finding the optimal treatment regime (or a series of sequentia
 l treatment regimes) based on individual characteristics has important app
 lications in precision medicine. We propose two new approaches to quantify
  uncertainty in optimal treatment regime estimation. First\, we consider i
 nference in the model-free setting\, which does not require to specify an 
 outcome regression model. Existing model-free estimators for optimal treat
 ment regimes are usually not suitable for the purpose of inference\, becau
 se they either have nonstandard asymptotic distributions or do not necessa
 rily guarantee consistent estimation of the parameter indexing the Bayes r
 ule due to the use of surrogate loss. We study a smoothed robust estimator
  that directly targets the parameter corresponding to the Bayes decision r
 ule for optimal treatment regimes estimation. We verify that a resampling 
 procedure provides asymptotically accurate inference for both the paramete
 r indexing the optimal treatment regime and the optimal value function. Ne
 xt\, we consider the high-dimensional setting and propose a semiparametric
  model assisted approach for simultaneous inference. Simulations results a
 nd real data examples are used for illustration. (Joint work with Yunan Wu
  and Haoda Fu)
LOCATION:https://maths-cam-ac-uk.zoom.us/j/93998865836?pwd=VzVzN1VFQ0xjS3V
 DdlY0enBVckY5dz09
END:VEVENT
END:VCALENDAR