BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Sharp Sensitivity Analysis for Inverse Propensity Weighting via Qu
 antile Balancing - Kevin Guo\, Stanford University
DTSTART:20210311T160000Z
DTEND:20210311T173000Z
UID:TALK157438@talks.cam.ac.uk
CONTACT:Qingyuan Zhao
DESCRIPTION:Inverse propensity weighting (IPW) is a popular method for est
 imating treatment effects from observational data. However\, its correctne
 ss relies on the untestable (and frequently implausible) assumption that a
 ll confounders have been measured. This paper introduces a robust sensitiv
 ity analysis for IPW that estimates the range of treatment effects compati
 ble with a given amount of unobserved confounding. The estimated range con
 verges to the narrowest possible interval (under the given assumptions) th
 at must contain the true treatment effect. Our proposal is a refinement of
  the influential sensitivity analysis by Zhao\, Small\, and Bhattacharya (
 2019)\, which we show gives bounds that are too wide even asymptotically. 
 This analysis is based on new partial identification results for Tan (2006
 )'s marginal sensitivity model.\n\nhttps://arxiv.org/abs/2102.04543
LOCATION:https://zoom.us/j/97791179955?pwd=eFMrTFNSRmhnTzBHdDBLZlgrTFRQdz0
 9
END:VEVENT
END:VCALENDAR