BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260624T014718EDT-6312BiVPln@132.216.98.100
DTSTAMP:20260624T054718Z
DESCRIPTION:Title: The Blessings of Multiple Causes\n\n \n\nAbstract: Causa
 l inference from observational data is a vital problem\, but it comes with
  strong assumptions. Most methods assume that we observe all confounders\,
  variables that affect both the causal variables and the outcome variables
 . But whether we have observed all confounders is a famously untestable as
 sumption. We describe the deconfounder\, a way to do causal inference from
  observational data allowing for unobserved confounding.\n\nHow does the d
 econfounder work? The deconfounder is designed for problems of multiple ca
 usal inferences: scientific studies that involve many causes whose effects
  are simultaneously of interest. The deconfounder uses the correlation amo
 ng causes as evidence for unobserved confounders\, combining unsupervised 
 machine learning and predictive model checking to perform causal inference
 . We study the theoretical requirements for the deconfounder to provide un
 biased causal estimates\, along with its limitations and tradeoffs. We dem
 onstrate the deconfounder on real-world data and simulation studies.\n
DTSTART:20191212T203000Z
DTEND:20191212T213000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Yixin Wang (Columbia University)
URL:/mathstat/channels/event/yixin-wang-columbia-unive
 rsity-303252
END:VEVENT
END:VCALENDAR