BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250714T041326EDT-1695BL3vxI@132.216.98.100
DTSTAMP:20250714T081326Z
DESCRIPTION:Title: Causal Inference with Unmeasured Confounding: an Instrum
 ental Variable Approach.\n\n \n\nAbstract: \n\nCausal inference is a chall
 enging problem because causation cannot be established from observational 
 data alone. Researchers typically rely on additional sources of informatio
 n to infer causation from association. Such information may come from powe
 rful designs such as randomization\, or background knowledge such as infor
 mation on all confounders. However\, perfect designs or background knowled
 ge required for establishing causality may not always be available in prac
 tice. In this talk\, I use novel causal identification results to show tha
 t the instrumental variable approach can be used to combine the power of d
 esign and background knowledge to draw causal conclusions. I also introduc
 e novel estimation tools to construct estimators that are robust\, efficie
 nt and enjoy good finite sample properties. These methods will be discusse
 d in the context of a randomized encouragement design for a flu vaccine.\n
 \n\n	Speaker\n\n\nLinbo Wang is an Assistant Professor in the Department of
  Statistical Sciences\, University of Toronto and Department of Computer a
 nd Mathematical Sciences\, University of Toronto Scarborough.\n\nPrior to 
 this\, he was a postdoc in the Harvard Causal Inference Program working wi
 th Eric Tchetgen Tchetgen and James Robins. He obtained a Ph.D. in Biostat
 istics from University of Washington in Mar 2016.\n
DTSTART:20190215T203000Z
DTEND:20190215T213000Z
LOCATION:Room 1205\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Dr. Linbo Wang (University of Toronto)
URL:/mathstat/channels/event/dr-linbo-wang-university-
 toronto-294559
END:VEVENT
END:VCALENDAR