BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Inference for Group Interaction Experiments - Cyrus Samii (New Yor
 k University)
DTSTART:20260121T101500Z
DTEND:20260121T110000Z
UID:TALK241801@talks.cam.ac.uk
DESCRIPTION:A common experimental research design is one in which individu
 als are randomly allocated into groups and then interact within the groups
  under different group-level treatment conditions. We present methods for 
 design-based inference for such ``group interaction'' experiments. A key c
 onsideration is that group interaction implies potential interference: an 
 individual's potential outcomes depend&nbsp\;on the groups to which others
  are allocated. This yields dependencies that should be accounted for when
  making inferential claims. We show that when group-member interference is
  present\, standard cluster-robust inference is consistent\, with referenc
 e to a superpopulation regime with sparse sampling\, in accounting for suc
 h dependencies for inference on marginalized causal effects that account f
 or interference. When interference is not present\, but groups are formed 
 through individually randomized assignment\, individual-level heteroskedas
 ticity robust inference is consistent for inference on the usual average t
 reatment effect.&nbsp\;\nJoint with Ye Wang and&nbsp\;Jiawei Fu
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR