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:69f41739c18c1
DTSTART;TZID=America/Toronto:20200129T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200129T100000
URL:https://uwaterloo.ca/statistics-and-actuarial-science/events/department
 -seminar-aya-mitani-harvard-th-chan-school-public
LOCATION:M3 - Mathematics 3 200 University Avenue West Room 3127 Waterloo O
 N N2L 3G1 Canada
SUMMARY:Department seminar by Aya Mitani\, Harvard T.H. Chan School of Publ
 ic\nHealth
CLASS:PUBLIC
DESCRIPTION:MARGINAL ANALYSIS OF MULTIPLE OUTCOMES WITH INFORMATIVE CLUSTER
  SIZE\n\n-------------------------\n\nPeriodontal disease is a serious inf
 ection of the gums and the bones\nsurrounding the teeth. In Veterans Affai
 rs Dental Longitudinal Study\n(VADLS)\, the relationships between periodon
 tal disease and other\nhealth and socioeconomic conditions are of interest
 . To determine\nwhether or not a patient has periodontal disease\, multipl
 e clinical\nmeasurements (clinical attachment loss\, alveolar bone loss\, 
 tooth\nmobility) are taken at the tooth-level. However\, a universal\ndefi
 nition for periodontal disease does not exist and researchers\noften creat
 e a composite outcome from these measurements or analyze\neach outcome sep
 arately. Moreover\, patients have varying number of\nteeth\, with those th
 at are more prone to the disease having fewer\nteeth compared to those wit
 h good oral health. Such dependence between\nthe outcome of interest and c
 luster size (number of teeth) is called\ninformative cluster size\, and re
 sults obtained from fitting\nconventional marginal models can be biased. I
 n this talk\, I will\nintroduce a novel method to jointly analyze multiple
  correlated\noutcomes for clustered data with informative cluster size usi
 ng the\nclass of generalized estimating equations (GEE) with cluster-speci
 fic\nweights. Using the data from VADLS\, I will compare the results\nobta
 ined from the proposed multivariate outcome cluster-weighted GEE\nto those
  from the conventional unweighted GEE. Finally\, I will discuss\na few oth
 er research settings where data may exhibit informative\ncluster size.
DTSTAMP:20260501T030009Z
END:VEVENT
END:VCALENDAR