Assessment of measurement equivalence with cross-national and longitudinal surveys in political science

Abstract

This paper emphasises the importance of assessing measurement equivalence when using cross-national and longitudinal surveys. We illustrate how to test for measurement equivalence using multiple group confirmatory factor analysis and clarify under what conditions both meaningful comparisons of construct means and relationships between constructs are possible. Using data from the International Social Survey Programme, empirical applications dealing with attitudes towards welfare policies are provided to illustrate the procedure. © 2012 European Consortium for Political Research.