Premium
Comparing Teachers’ Job Satisfaction across Countries: A Multiple‐Pairwise Measurement Invariance Approach
Author(s) -
Zieger Laura,
Sims Sam,
Jerrim John
Publication year - 2019
Publication title -
educational measurement: issues and practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.158
H-Index - 52
eISSN - 1745-3992
pISSN - 0731-1745
DOI - 10.1111/emip.12254
Subject(s) - measurement invariance , equivalence (formal languages) , pairwise comparison , job satisfaction , psychology , social psychology , econometrics , mathematics , statistics , structural equation modeling , confirmatory factor analysis , discrete mathematics
There is much interest in comparing latent traits, such as teacher job satisfaction, in large international surveys. However, different countries respond to questionnaires in different languages and interpret the questions through different cultural lenses, raising doubts about the psychometric equivalence of the measurements. Making valid comparisons depends on the latent traits displaying scalar measurement invariance. Unfortunately, this condition is rarely met across many countries at once. Different approaches that maximize the utility of such surveys, but remain faithful to the principles of measurement invariance testing, are therefore needed. This article illustrates one such approach, involving multiple‐pairwise comparisons. This enables us to compare teacher job satisfaction in England to 17 of the countries that participated in TALIS 2013. Teacher job satisfaction in England was as low, or lower, than all of the 17 comparable countries.