Statisticians have developed scoring rules for evaluating probabilistic forecasts against observations. However, there are very few applications in the literature on population forecasting. A scoring rule measures the distance between the predictive distribution and its outcome. We review scoring rules that reward accuracy (the outcome is close to the expectation of the distribution) and sharpness (the distribution has low variance, which makes it difficult to hit the target). We evaluate probabilistic population forecasts for France, the Netherlands, and Norway. Forecasts for total population size for the Netherlands and for Norway performed quite well. The error in the jump-off population caused a bad score for the French forecast. We evaluate the age and sex composition predicted for the year 2010. The predictions for the Netherlands received the best scores, except for the oldest old. The age pattern for the Norwegian score reflects the under-prediction of immigration after the enlargement of the European Union in 2005.

Citation: Keilman, N. (2020). Evaluating Probabilistic Population Forecasts. Economie et Statistique / Economics and Statistics, 520‑521, 49–64.
https://doi.org/10.24187/ecostat.2020.520d.2033