BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unbiased Set-Estimation of Heterogeneous Causal Effects - Ganesh K
 arapakula (University of Cambridge)
DTSTART:20220606T123000Z
DTEND:20220606T140000Z
UID:TALK175283@talks.cam.ac.uk
CONTACT:Qingyuan Zhao
DESCRIPTION:It has long been known that the inverse probability weighting 
 (IPW) methods for estimating causal effects can be very unstable and can e
 xplode in certain settings\, such as limited overlap. Several workarounds\
 , such as trimming of the propensity scores\, have been suggested in the r
 ecent literature\, but the issue persists and goes hand in hand with the f
 inite-sample bias of IPW-based estimators. To address the issue of bias\, 
 this paper proposes finite-sample 'unbiased set-estimators' (based on a ge
 neralization of the concept of unbiased point estimation) of heterogeneous
  causal effects in a common observational setting where unconfoundedness i
 s plausible within fine strata (either predetermined or formed based on hi
 gh-dimensional clustering algorithms) using large-scale data. These estima
 tors are inspired by an in-depth investigation of a problematic ratio in c
 ausal inference: the reciprocal of the estimated propensity score. This pa
 per also proposes asymptotically unbiased double-robust point-estimators i
 n more general settings where causal effects are heterogeneous. Finite-sam
 ple and large-sample statistical inference methods are also proposed for q
 uantifying statistical uncertainty. A byproduct of these methods is a fini
 te-sample Fisherian frequentist alternative to the Bayesian posterior dist
 ribution for the causal effects. The proposed methods are empirically demo
 nstrated using data from the widely analyzed National Supported Work progr
 am to enable empirical comparisons with other methods suggested in the lit
 erature. Simulation exercises are also conducted to evaluate the practical
  performance of the new procedures.
LOCATION:MR11 (B1.39)\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB
END:VEVENT
END:VCALENDAR