Finite Mixture Multilevel Multidimensional Ordinal IRT Models for Large Scale Cross-Cultural Research Export

@article{citeulike:5497578, abstract = {Abstract\ \ 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.}, author = {de Jong, Martijn and Steenkamp, Jan-Benedict}, citeulike-article-id = {5497578}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s11336-009-9134-z}, citeulike-linkout-1 = {http://www.springerlink.com/content/t173308346721vl2}, doi = {10.1007/s11336-009-9134-z}, journal = {Psychometrika}, keywords = {bayesian, irt, latentvariable, mcmc, mixture, multilevel, nonparametrics}, posted-at = {2009-10-21 18:35:49}, priority = {2}, title = {Finite Mixture Multilevel Multidimensional Ordinal IRT Models for Large Scale Cross-Cultural Research}, url = {http://dx.doi.org/10.1007/s11336-009-9134-z} }

TY - JOUR ID - citeulike:5497578 L3 - citeulike-article-id:5497578 N2 - Abstract  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. JF - Psychometrika TI - Finite Mixture Multilevel Multidimensional Ordinal IRT Models for Large Scale Cross-Cultural Research KW - bayesian KW - irt KW - latentvariable KW - mcmc KW - mixture KW - multilevel KW - nonparametrics AU - de Jong, Martijn AU - Steenkamp, Jan-Benedict UR - http://dx.doi.org/10.1007/s11336-009-9134-z ER -