MIPEX are currently launching their latest release (with a shiny new website), and their data are often used in academic research. Earlier I have shown that the MIPEX can indeed be used as scales — as it is often done –, although there is scope for improving these scales. Put differently, from a statistical point of view, the dimensions and sub-dimensions in the MIPEX data are not optimal. There are two approaches to this: First, we can reduce the data complexity by removing items that are not strongly associated. Second, we can use the redundancy in the data, and pick and mix the data.
In a paper just published in the SSQ, I demonstrate this by recombining bits and pieces of the MIPEX to create citizenship scores that closely match those in Koopmans et al. On the one hand, this is a demonstration that we can easily create more valid constructs when recombining existing data sources like the MIPEX. On the other hand, I have gained classifications of citizenship models in many more countries than previous endeavours — with less effort. As a side product, I can validate the citizenship typology presented by Koopmans et al. by showing the existence of ethnic-pluralistic citizenship models (segregationism), previously only predicted on a theoretical basis.
Koopmans, Ruud, Paul Statham, Marco Giugni, and Florence Passy. 2005. Contested Citizenship: Immigration and Cultural Diversity in Europe. Minneapolis: Minnesota University Press.
Ruedin, Didier. 2015. “Increasing Validity by Recombining Existing Indices: MIPEX as a Measure of Citizenship Models.” Social Science Quarterly. doi:10.1111/ssqu.12162.