One of the most recent development in the field of Item Response Theory (IRT) has been the evaluation of IRT models as multilevel model (MLIRT). This method is designed to meet some challenges such as estimating item difficulty and person parameters simultaneously, including explanatory variables at different levels of a hierarchy and group membership in the models. This paper explores the performance of two-parameter multilevel IRT model in order to have insights into the sources of welfare attitudes among European citizens. Attitudes towards welfare encompass a broad spectrum of aspects. Here, we focus on attitudes towards welfare state scope and responsibilities and taxation and financing. The estimates of the parameters of interest are obtained within a Bayesian framework, using a Markov Chain Monte Carlo method.
Welfare attitudes in Europe: an application of IRT models to ESS data
DI ZIO, Simone;FONTANELLA, Lara;SARRA A.
2011-01-01
Abstract
One of the most recent development in the field of Item Response Theory (IRT) has been the evaluation of IRT models as multilevel model (MLIRT). This method is designed to meet some challenges such as estimating item difficulty and person parameters simultaneously, including explanatory variables at different levels of a hierarchy and group membership in the models. This paper explores the performance of two-parameter multilevel IRT model in order to have insights into the sources of welfare attitudes among European citizens. Attitudes towards welfare encompass a broad spectrum of aspects. Here, we focus on attitudes towards welfare state scope and responsibilities and taxation and financing. The estimates of the parameters of interest are obtained within a Bayesian framework, using a Markov Chain Monte Carlo method.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
