BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251105T170450EST-1220tAMV4l@132.216.98.100
DTSTAMP:20251105T220450Z
DESCRIPTION:Dimension Reduction for Causal Inference\n\n\n	Abstract:\n\n\nIn
  this talk\, we discuss how sufficient dimension reduction can be used to 
 aid causal inference. We propose a new matching approach based on the redu
 ced covariates obtained from sufficient dimension reduction. Compared with
  the original covariates and the propensity scores\, which are commonly us
 ed for matching in the literature\, the reduced covariates are estimable n
 onparametrically and are effective in imputing the missing potential outco
 mes. Under the ignorability assumption\, the consistency of the proposed a
 pproach requires a weaker common support condition than the one we often a
 ssume for propensity score-based methods. We develop asymptotic properties
 \, and conduct simulation studies as well as real data analysis to illustr
 ate the proposed approach.\n\n\n	Speaker\n\n\nYeying Zhu is an Assistant Pr
 ofessor in the Department of Statistics and Actuarial Science at the Unive
 rsity of Waterloo. Her research interest lies in causal inference\, machin
 e learning and the interface between the two. Her current work focuses on 
 the inverse weighted estimation of causal effects using propensity scores 
 and marginal structural models.\n
DTSTART:20181005T193000Z
DTEND:20181005T203000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Yeying Zhu (University of Waterloo)
URL:/mathstat/channels/event/yeying-zhu-university-wat
 erloo-290408
END:VEVENT
END:VCALENDAR