BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Disentangling confounding and nonsense associations due to depende
 nce
DTSTART:20210305T151500
DTEND:20210305T163000
DTSTAMP:20260509T234250Z
UID:373cc0e7c162ab2feeb852f5c664e50446a6dc0e1eca013efe831c5d
CATEGORIES:Conferences - Seminars
DESCRIPTION:Elizabeth L. Ogburn\, Johns Hopkins\nNonsense associations ca
 n arise when an exposure and an outcome of interest exhibit similar patter
 ns of dependence. Confounding is present when potential outcomes are not
  independent of treatment.\nThis talk will describe how confusion about th
 ese two phenomena results in shortcomings in popular methods in two areas:
  (1) causal inference with multiple treatments and unmeasured confounding 
 and (2) causal and statistical inference with social network data.\nFor ea
 ch of these areas I will demonstrate the flaws in existing methods and des
 cribe new methods that were inspired by careful consideration of dependenc
 e and confounding.\n 
LOCATION:https://epfl.zoom.us/j/87164726100
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR