A longitudinal cross country comparison of migrant integration policies via mixture of matrix-normals

In recent decades, there has been a growing research interest in comparative studies of migrant integration, assimilation and the evaluation of policies implemented for these purposes. With this aim, the Migrant Integration Policy Index (MIPEX) measures policies to integrate migrants in 52 countries all over the world, over time. However, the comparison of very different countries on complex and multidimensional phenomena can lead to misleading interpretations and evaluations of the results. In this paper, we improve and facilitate the comparison between the treated countries on 7 MIPEX dimensions, applying a Mixture of Matrix-Normals classification model for longitudinal data. Trough the analysis, 5 clusters of countries have been discovered, allowing us to add new levels of interpretation of the data.