LC-IRT models with covariates in Polish job satisfaction analysis

• Main Author: Genge, Ewa
• Format: Article in Journal/Newspaper
• Language: English
• Published: Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu 2020
• Subjects: Norway; Iceland
• Online Access: https://dbc.wroc.pl/dlibra/publication/edition/75781/content

Argumenta Oeconomica, 2020, Nr 1 (44), s. 207-226 Employment is at the heart of European Union (EU) policies as it is the basis for wealth creation. Knowing how satisfied EU residents are with their occupation is very important, since losing one’s job may undermine one’s life satisfaction and its overall meaning (European Commission 2015). According to the most recent Eurostat data (European Commission 2017), Poland reported an average job satisfaction well above the EU mean, ranked 8th (behind Denmark, Iceland, Austria, Finland, Norway, Switzerland and Sweden). Thus, it is interesting to present an analysis focused on the job satisfaction of workers in Poland – a country of emigration, with the highest percentage of temporary contracts in Europe (European Commission 2016). The main aim of our study is understanding how the different socio-economic features affect the groups of workers with similar job satisfaction levels in Poland. Most of the Polish job satisfaction studies are focused on selected professional groups, in selected regions of Poland. This article presents another, the latent variable models approach to the hetero-geneous data set for different subgroups of workers in all the regions of Poland. The combination of the two latent variable models enables to find homogeneous classes of individuals characterized by the similar latent ability levels, and at the same time, the item characteristics analysis (usually identified as discrimination indices and difficulty parameters) as well. Latent Class Item Response Theory (LC-IRT) models are more flexible in compa-rison with traditional formulations of Item Response Theory (IRT) models, often based on restrictive assumptions, such as normality of latent trait (explicitly introduced). Moreover, the authors also apply the extended latent variable models under the discrete assumption of the latent trait including individual socio-demographic features, such as age, sex, education, marital status or current financial situation. The article analyzes data ...