BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250225T112049
DTSTART;TZID=America/Detroit:20250225T120000
DTEND;TZID=America/Detroit:20250225T130000
SUMMARY:Workshop / Seminar:\"Brown Bag\" Seminar with Wei Jin\, PhD
DESCRIPTION:Johns Hopkins UniversityDepartment of Applied Mathematics and StatisticsPostdoctoral Fellow\nTitle: Robust Bayesian Learning for Individualized Treatment Rules Under Unmeasured Confounding\nAbstract: Data-driven personalized decision-making has become increasingly important in many scientific fields. Most existing methods rely on the assumption of no unmeasured confounding to establish causal inferences before proceeding with decision-making for identifying the optimal individualized treatment rule (ITR). However\, this assumption is often violated in practice\, especially in observational studies. While techniques like instrumental variables or proxy variables can help address unmeasured confounding\, such additional data sources are not always available. Moreover\, robustly learning the optimal ITR from observational data is challenging when data are unbalanced\, where certain combinations of treatments and patient characteristics are underrepresented. In this talk\, I will introduce a novel Bayesian approach to robustly learn the optimal ITR for continuous treatments under unmeasured confounding. For causal identification\, we propose a Bayesian causal model that achieves unique identification under certain mild distributional assumptions\, without requiring additional data sources. For policy optimization\, we develop a practical algorithm that robustly learns the optimal ITR by identifying a conservative policy. Through simulations and an application to a large-scale kidney transplantation dataset\, we demonstrate the proposed method’s identifiability\, utility\, and robustness\, highlighting its value in advancing precision medicine.\nNOTE: Lunch will be provided after the seminar for all attendees.
UID:132881-21872012@events.umich.edu
URL:https://events.umich.edu/event/132881
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Sessions
LOCATION:SPH I, Room 1680 (Cornely Community Room)
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250225T112049
DTSTART;TZID=America/Detroit:20250225T120000
DTEND;TZID=America/Detroit:20250225T130000
SUMMARY:Workshop / Seminar:\"Brown Bag\" Seminar with Wei Jin\, PhD
DESCRIPTION:Johns Hopkins UniversityDepartment of Applied Mathematics and StatisticsPostdoctoral Fellow\nTitle: Robust Bayesian Learning for Individualized Treatment Rules Under Unmeasured Confounding\nAbstract: Data-driven personalized decision-making has become increasingly important in many scientific fields. Most existing methods rely on the assumption of no unmeasured confounding to establish causal inferences before proceeding with decision-making for identifying the optimal individualized treatment rule (ITR). However\, this assumption is often violated in practice\, especially in observational studies. While techniques like instrumental variables or proxy variables can help address unmeasured confounding\, such additional data sources are not always available. Moreover\, robustly learning the optimal ITR from observational data is challenging when data are unbalanced\, where certain combinations of treatments and patient characteristics are underrepresented. In this talk\, I will introduce a novel Bayesian approach to robustly learn the optimal ITR for continuous treatments under unmeasured confounding. For causal identification\, we propose a Bayesian causal model that achieves unique identification under certain mild distributional assumptions\, without requiring additional data sources. For policy optimization\, we develop a practical algorithm that robustly learns the optimal ITR by identifying a conservative policy. Through simulations and an application to a large-scale kidney transplantation dataset\, we demonstrate the proposed method’s identifiability\, utility\, and robustness\, highlighting its value in advancing precision medicine.\nNOTE: Lunch will be provided after the seminar for all attendees.
UID:132881-21872013@events.umich.edu
URL:https://events.umich.edu/event/132881
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Sessions
LOCATION:Virtual
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20250130T121527
DTSTART;TZID=America/Detroit:20250225T120000
DTEND;TZID=America/Detroit:20250225T130000
SUMMARY:Meeting:Central Campus Lunch with the Deans
DESCRIPTION:\nWant a chance to meet and chat with the Rackham Deans? Come join us at Lunch with the Deans series! The Rackham Student Government will be hosting two Lunch with the Deans events at the following dates and locations:\nStudents can provide their thoughts and ask questions. Students who are unable to attend\, but have questions for the Deans are encouraged to submit questions to us via email (rsg-exec@umich.edu) or in the RSVP. RSVP is highly recommended.\nRegister at https://myumi.ch/3QNEA.\n\nWe want to ensure full and equitable participation in our events. If an accommodation would promote your full participation in this event\, please follow the registration link to indicate your accommodation requirements. Please let us know as soon as possible in order to have adequate time\, preferably one week\, to arrange for your requested accommodations or an effective alternative.
UID:132092-21869944@events.umich.edu
URL:https://events.umich.edu/event/132092
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Graduate Students
LOCATION:Rackham Graduate School (Horace H.)
CONTACT:
END:VEVENT
END:VCALENDAR