BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20191103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69d933cab9718
DTSTART;TZID=America/Toronto:20200120T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200120T100000
URL:https://uwaterloo.ca/statistics-and-actuarial-science/events/department
 -seminar-jared-huling-ohio-state-university
LOCATION:M3 - Mathematics 3 200 University Avenue West Room 3127 Waterloo O
 N N2L 3G1 Canada
SUMMARY:Department seminar by Jared Huling\, Ohio State University
CLASS:PUBLIC
DESCRIPTION:SUFFICIENT DIMENSION REDUCTION FOR POPULATIONS WITH STRUCTURED\
 nHETEROGENEITY\n\nRisk modeling has become a crucial component in the effe
 ctive delivery\nof health care. A key challenge in building effective risk
  models is\naccounting for patient heterogeneity among the diverse populat
 ions\npresent in health systems. Incorporating heterogeneity based on the\
 npresence of various comorbidities into risk models is crucial for the\nde
 velopment of tailored care strategies\, as it can provide\npatient-centere
 d information and can result in more accurate risk\nprediction. Yet\, in t
 he presence of high dimensional covariates\,\naccounting for this type of 
 heterogeneity can exacerbate estimation\ndifficulties even with large samp
 le sizes. Towards this aim\, we\npropose a flexible and interpretable risk
  modeling approach based on\nsemiparametric sufficient dimension reduction
 . The approach accounts\nfor patient heterogeneity\, borrows strength in e
 stimation across\nrelated subpopulations to improve both estimation effici
 ency and\ninterpretability\, and can serve as a useful exploratory tool or
  as a\npowerful predictive model. In simulated examples\, we show that our
 \napproach can improve estimation performance in the presence of\nheteroge
 neity and is quite robust to deviations from its key\nunderlying assumptio
 n. We demonstrate the utility of our approach in\nthe prediction of hospit
 al admission risk for a large health system\nwhen tested on further follow
 -up data.
DTSTAMP:20260410T173050Z
END:VEVENT
END:VCALENDAR