BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Confidence intervals for IRT models: three new exact approaches me
 eting different criteria of optimality - Anna Doebler - WWU Münster
DTSTART:20100527T090000Z
DTEND:20100527T100000Z
UID:TALK24987@talks.cam.ac.uk
CONTACT:Michal Kosinski
DESCRIPTION:A common way to calculate confidence intervals in a testing si
 tuation is to assume that the standardised maximum likelihood estimator fo
 r the person parameter is normally distributed. Although maximum likelihoo
 d estimators are approximately normally distributed\, this assumption is o
 ften questionable for short and medium test length. For example\, when wor
 king with the Rasch model and a test length of n\, there are only n + 1 di
 fferent possible outcomes of the estimation and so the distribution of the
  standardized estimator will be quite discrete. Another disadvantage of th
 e standard approach is that even when the normality assumption holds\, it 
 is not clear if the obtained confidence intervals meet any criterion of op
 timality\, for example regarding some notion of "smallness”. A third und
 esirable property is that they will always depend on the specific choice o
 f the estimator. Therefore\, we will try to define confidence intervals in
  a more "exact" way by making use of the relationship between confidence i
 ntervals and hypothesis testing. We will outline three different approache
 s for confidence interval constructions and discuss how far these meet dif
 ferent optimality criteria.
LOCATION:Seminar Room\, The Mond Building\, New Museums Site
END:VEVENT
END:VCALENDAR