BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251006T174629EDT-8303a8sdtu@132.216.98.100
DTSTAMP:20251006T214629Z
DESCRIPTION:Edward H. Kennedy\, PhD Candidate\n\nResearch Assistant\, Depar
 tment of Biostatistics\, University of Pennsylvania\n\nRobust causal infer
 ence with continuous treatments\n\nALL ARE WELCOME\n\nAbstract:\n\nContinu
 ous treatments (e.g.\, doses) arise often in practice\, but available caus
 al effect estimators are limited: they either require parametric models fo
 r the effect curve\, or else do not allow for doubly robust covariate adju
 stment. This is an example of a more general problem: if we want to use st
 andard semiparametric approaches then we must live with low-dimensional es
 timands\, while if we want to pursue more complex estimands then typically
  we must rely on plug-in estimation (which is sensitive to the curse of di
 mensionality). To solve this problem in the continuous treatment effect se
 tting\, we develop a novel doubly robust kernel smoothing approach that re
 quires only mild smoothness assumptions on the effect curve\, and still al
 lows for misspecification of either the treatment density or outcome regre
 ssion (i.e.\, gives small second-order estimation bias). We derive asympto
 tic properties and propose a procedure for data-driven bandwidth selection
 . The methods are illustrated in a study of the effect of nurse staffing o
 n hospital readmissions penalties.\n\nBio:\n\nEdward Kennedy is a PhD stud
 ent in biostatistics at the University of Pennsylvania.  His research inte
 rests include causal inference\, high-dimensional data\, and non- and semi
 -parametric methods\, among other topics.  He is also particularly interes
 ted in applications in health services research\, medicine and public poli
 cy.\n\nPlease visit: www.edwardhkennedy.weebly.com\n
DTSTART:20151124T203000Z
DTEND:20151124T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Special Seminar
URL:/epi-biostat-occh/channels/event/special-seminar-2
 56315
END:VEVENT
END:VCALENDAR