BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
PRODID:Data::ICal 0.24
BEGIN:VTIMEZONE
TZID:Pacific/Auckland
X-LIC-LOCATION:Pacific/Auckland
BEGIN:DAYLIGHT
DTSTART:19700927T020000
RRULE:FREQ=YEARLY;BYMONTH=9;BYDAY=-1SU
TZNAME:NZDT
TZOFFSETFROM:+1200
TZOFFSETTO:+1300
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19700405T030000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
TZNAME:NZST
TZOFFSETFROM:+1300
TZOFFSETTO:+1200
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:SMS Seminars
CONTACT:Thomas Suesse\, PhD student
DESCRIPTION:Surveys often contain qualitative variables for which responden
 ts may select \nany number of the outcome categories. This type of respons
 e is called \nmultiple responses. Each outcome category refers to an item\
 , where the items \nare dependent. Agresti and Liu (2001) introduced margi
 nal models based on \nthe marginal counts of each item. The models describ
 e the association \nbetween items and some explanatory variables taking th
 e dependence into \naccount. The model fitting has at least two approaches
 . One is called the \ngeneralized estimation equations (GEE) method and th
 e other is called the \nmaximum likelihood (ML) estimation for homogeneous
  linear predictor (HLP) \nmodels (Lang\, 2005).\nWe will discuss MMI hypot
 hesis testing\, dually consistent odds ratio \nestimators\, more efficient
  use of correlation estimation for GEE and \ndeletion diagnostics for ML a
 nd GEE estimation.\nEstimation of the odds ratio for stratified multiple r
 esponses for sparse \ndata having dependent or independent strata will als
 o be discussed.\nAn extension of multiple responses are repeated multiple 
 responses. Model \napproaches will be outlined as well as future work.
DTEND;TZID=Pacific/Auckland:20060811T130000
DTSTAMP:20260531T171532Z
DTSTART;TZID=Pacific/Auckland:20060811T120000
LOCATION:Seminar Room\, Cotton 249
ORGANIZER:Thomas Suesse\, PhD student
SUMMARY:Thomas Suesse\, PhD student - "Analysis and Diagnostics for Multipl
 e Categorical Responses"
UID:seminar_sms427_20060811120000
URL:
END:VEVENT
END:VCALENDAR