Reference : On the finiteness and uniqueness of the weighted likelihood estimator of ability in p...
Scientific congresses and symposiums : Unpublished conference/Abstract
Social & behavioral sciences, psychology : Education & instruction
http://hdl.handle.net/2268/173233
On the finiteness and uniqueness of the weighted likelihood estimator of ability in polytomous IRT models
English
Magis, David mailto [Université de Liège - ULiège > Département Education et formation > Psychométrie et édumétrie >]
Verhelst, Norman []
21-Nov-2014
Yes
No
International
RCEC workshop on Item Response Theory and Educational Measurement
19-21 novembre 2014
Research Center for Examinations and Certification
Twente
Pays-Bas
[en] Item response theory ; polytomous models ; weighted likelihood estimation ; finiteness ; uniqueness
[en] In item response theory (IRT), the weighted likelihood (WL) estimator has become a central method to estimate ability levels of respondents. Primarily introduced with dichotomous IRT models (Warm, 1989), it was later extended to polytomous IRT models (Samejima, 1998). However, very few information is available about the behavior of the WL estimator, and especially about the uniqueness of the ability estimates as well as their finiteness.
The purpose of this talk is to establish that with polytomous item response models, the WL estimator of ability always returns finite values. This result is valid for the class of difference models and divide-by-total models, independently of the number of items and the response patterns. However, such estimates may not necessarily be unique, as the WL solving equation may provide several optimal values. Some examples are considered to illustrate both findings.
http://hdl.handle.net/2268/173233

File(s) associated to this reference

Additional material(s):

File Commentary Size Access
Private access
RCEC 2014 - David Magis.pdf1.32 MBRequest copy
Private access
R code RCEC talk.R416 BRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.