BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Estimation of Causal Effects in Network-Dependent Observational Da
 ta - Oleg Sofrygin (University of California\, Berkeley)
DTSTART:20160712T143000Z
DTEND:20160712T150000Z
UID:TALK66719@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>Co-author: Mark J. van der Laan (University of  Californ
 ia\, Berkeley\, CA) <br></span> <span><br>We outline the framework of targ
 eted maximum likelihood estimation (TMLE) in  observational network data. 
 Consider a dataset in which each observational unit  is causally connected
  to other units via a known social or geographical network.  For each unit
  we observe their baseline covariates\, their exposure and their  outcome\
 , and we are interested in estimating the effect of a single time-point  s
 tochastic intervention. We propose a semi-parametric statistical model tha
 t  allows for between-unit dependencies: First\, unit-level exposure can d
 epend on  the baseline covariates of other connected units. Second\, the u
 nit-level outcome  can depend on the baseline covariates and exposures of 
 other connected units. We  impose some restrictions on our model\, e.g.\, 
 assuming that the unit&#39\;s exposure  and outcome depend on other units 
 as some known (but otherwise arbitrary)  summary measures of fixed dimensi
 onality. A practical application of our  approach is demonstrated in a lar
 ge-scale networ k simulation study that applies  two newly developed R pac
 kages: simcausal and tmlenet. We also discuss some  extensions of our work
  towards estimation in longitudinal data.</span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR