http://hdl.handle.net/1765/16806
http://dx.doi.org/10.1007/s11336-009-9134-z
scopus: cited 5 times
web of science: cited 1 time
http://dx.doi.org/10.1007/s11336-009-9134-z
scopus: cited 5 times
web of science: cited 1 time
Finite Mixture Multilevel Multidimensional Ordinal IRT Models for Large Scale Cross-Cultural Research
January 2009
Article
volume 75, issue 1 pp 3-32.
This publication is part of collection
| Related Files |
|---|
View PDF Version
(PK_martijnJB.pdf, 0.6MB) |
|
Redirect to publisher's version
(publisher's version.url.txt, 43 bytes) |
We present a class of finite mixture multilevel multidimensional ordinal IRT models for large scale cross-cultural research. Our model is proposed for confirmatory research settings. Our prior for item parameters is a mixture distribution to accommodate situations where different groups of countries have different measurement operations, while countries within these groups are still allowed to be heterogeneous. A simulation study is conducted that shows that all parameters can be recovered. We also apply the model to real data on the two components of affective subjective well-being: positive affect and negative affect. The psychometric behavior of these two scales is studied in 28 countries across four continents.
Keywords
- cross-cultural research
- item response theory
- differential item functioning
- graded response model
- hierarchical item response theory
- measurement equivalence
- measurement invariance
- mixture modeling
- latent classes
- multidimensional IRT
Automatically Extracted Terms
- model
- country
- parameter
- measurement
- score
- invariance
- group
- item parameters
- research
- response
- distribution
- item response theory
- scale
- class
- psychometrika
- jan-benedict e.m
- variance
- sample
- mixture
- sum scores
