BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Tutorial on Identification\, Non-Identification\, and Parameteri
 zations in Causal Graphs with Hidden Variables (Part 1) - Rohit Bhattachar
 ya (Williams College)
DTSTART:20260119T140000Z
DTEND:20260119T150000Z
UID:TALK241768@talks.cam.ac.uk
DESCRIPTION:Causal graphical models\, especially those involving hidden va
 riables\, have emerged as an important tool in applied research and as mat
 hematically intriguing objects in their own right. In keeping with the the
 me of this programme\, I will blend theory and practice in my treatment of
  these models. The first part of the tutorial covers the foundations of ca
 usal graphs&mdash\;how they are defined\, why they are useful\, and classi
 cal identification results\, including the g-formula\, front-door formula\
 , and an introduction to discrete parameterizations of these models. The t
 utorial also emphasizes results on non-identification\, characterizing set
 tings in which unbiased inference is impossible without additional assumpt
 ions. The second part provides a brief introduction to key ideas in model 
 selection for adjudicating between competing causal models when there is m
 odel uncertainty. The overarching goal of the tutorial is to equip attende
 es with a fairly general framework and knowledge that allow them to engage
  more confidently with both theoretical and applied problems in causal inf
 erence.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR