|
Abstract
|
Multilevel models (MLMs) are flexible in that they can be employed to obtain item and person
parameters, test for differential item functioning (DIF) and capture both local item and person
dependence. Papers on the MLM analysis of item response data have focused mostly on theoretical
issues where applications have been add-ons to simulation studies with a methodological focus.
Although the methodological direction was necessary as a first step to show how MLMs can be
utilized and extended to model item response data, the emphasis needs to be shifted towards
providing evidence on how applications of MLMs in educational testing can provide the benefits
that have been promised. The present study uses foreign language reading comprehension data to
illustrate application of hierarchical generalized models to estimate person and item parameters,
differential item functioning (DIF), and local person dependence in a three-level model.
|