BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260901T092546EDT-25877vHou4@132.216.98.100
DTSTAMP:20260901T132546Z
DESCRIPTION:✒️ TITLE / TITRE\n\nFighting Noise with Noise: Causal Inference
  with Many Candidate Instruments.\n\n📄 ABSTRACT / RÉSUMÉ\n\nInstrumental v
 ariable methods provide useful tools for inferring causal effects in the p
 resence of unmeasured confounding. To apply these methods with large-scale
  data sets\, a major challenge is to find valid instruments from a possibl
 y large candidate set. In practice\, most of the candidate instruments are
  often not relevant for studying a particular exposure of interest. Moreov
 er\, not all relevant candidate instruments are valid as they may directly
  influence the outcome of interest. In this work\, we propose a data-drive
 n method for causal inference with many candidate instruments that address
 es these two challenges simultaneously. A key component of our proposal in
 volves using pseudo variables\, known to be irrelevant\, to remove variabl
 es from the original set that exhibit spurious correlations with the expos
 ure. Synthetic data analyses show that the proposed method performs favour
 ably compared to existing methods. We apply our method to a Mendelian rand
 omization study estimating the effect of obesity on health-related quality
  of life.\n\n📍 PLACE /  LIEU \n	Hybride - Concordia\, Salle / Room LB921-4
 \n\n \n\n\n	\n		\n			\n				Lien ZOOM Link\n			\n		\n	\n\n
DTSTART:20260327T193000Z
DTEND:20260327T203000Z
SUMMARY:Dehan Kong  (University of Toronto)
URL:https://www.mcgill.ca/mathstat/channels/event/dehan-kong-university-tor
 onto-372080
END:VEVENT
END:VCALENDAR