Migration Studies with a Compositional Data Approach: A Case Study of Population Structure in the Capital Region of Denmark

Abstract

Computing percentages or proportions for removing the influence of population density has recently gained popularity, as it offers a deep insight into compositional variability. However, data are constrained to a constant sum and therefore are not independent observations, a fundamental limitation for applying standard multivariate statistical tools. Compositional Data (CoDa) techniques address the issue of standard statistical tools being insufficient for the analysis of closed data (i.e., spurious correlations, predictions outside the range, and sub-compositional incoherence) but they are not widely used in the field of population geography. Hence, in this article, we present a case study where we analyse at parish level the spatial distribution of Danes, Western migrants and non-Western migrants in the Capital region of Denmark. By applying CoDa techniques, we have been able to identify the spatial population segregation in the area and we have recognised patterns in the distribution of various demographic groups that can be used for interpreting housing prices variations. Our exercise is a basic example of the potentials of CoDa techniques which generate more robust and reliable results than standard statistical procedures in order to interpret the relations among various demographic groups. It can be further generalised to other population datasets with more complex structures.

Disaggregation of population estimates at high spatial resolution with machine learning

“…11). Using the openly available data at parish level, the relations between Danes, Western and non-Western migrants were also explored using compositional data [CoDa; 5, 6] techniques [37].…”