To project Denmark’s population, we pulled data from Danmarks Statistik, Denmark’s official statistical office. Using historical trends, and assuming the current activity prevails, we were able to establish a reasonable expectation for predicting future population values.

We used two models for these population projections: The Monte Carlo and the Autoregression Integrated Moving Average (ARIMA) models. In each of Denmark’s metro areas, we ran multiple configurations of each of the two models to find out which model (and which configuration within that model) was most accurate for that metro.

Denmark’s metropolitan areas were hand-curated based on the country’s NUTS 4 municipalities. The Nomenclature of Territorial Units for Statistics (NUTS) geographical division is constructed by Eurostat. Note that the NUTS4 tier is now called LAU1. More information about the Local Administrative Units (LAU)established by Eurostat can be found here. Furthermore, the metros were adjusted to reflect the country’s 2007 administrative reform.

We pulled Denmark’s labor market information (LMI) from three sources:

Denmark uses its own classification system DBO7 (Danske Branchekode 2007) which is a variation of NACE Rev. 2. Figures were conformed to standard NACE Rev. 2 prior to use in the estimation of employment by occupation.

Finally, when creating the occupation supply projections, we took the expected population growth rate from the models mentioned above and applied that same growth rate across the LMI in each Danish metropolitan area. Once we had the projections, we mapped the newly aggregated International Standard Classification of Occupations (ISCO-08) to Global Occupations.