Volume 6 - Article 15 | Pages 409–454  

Why population forecasts should be probabilistic - illustrated by the case of Norway

By Nico Keilman, Dinh Quang Pham, Arve Hetland

Abstract

Deterministic population forecasts do not give an appropriate indication of forecast uncertainty. Forecasts should be probabilistic, rather than deterministic, so that their expected accuracy can be assessed.
We review three main methods to compute probabilistic forecasts, namely time series extrapolation, analysis of historical forecast errors, and expert judgement. We illustrate, by the case of Norway up to 2050, how elements of these three methods can be combined when computing prediction intervals for a population’s future size and age-sex composition. We show the relative importance for prediction intervals of various sources of variance, and compare our results with those of the official population forecast computed by Statistics Norway.

Author's Affiliation

• Nico Keilman - Universitetet i Oslo, Norway EMAIL
• Dinh Quang Pham - Statistisk sentralbyrå (Statistics Norway), Norway EMAIL
• Arve Hetland - Statistisk sentralbyrå (Statistics Norway), Norway EMAIL

Other articles by the same author/authors in Demographic Research

Editorial: The past, present, and future of Demographic Research
Volume 41 - Article 41

Mortality shifts and mortality compression in period and cohort life tables
Volume 41 - Article 40

Probabilistic household forecasts based on register data- the case of Denmark and Finland
Volume 28 - Article 43

An editorial on plagiarism
Volume 24 - Article 17

Most recent similar articles in Demographic Research

Changes in birth seasonality in Spain: Data from 1863–1870 and 1900–2021
Volume 49 - Article 35    | Keywords: Box-Jenkins method, Cosinor analysis, Fourier analysis, season of birth, seasonality, time series, vital statistics

The COVID-19 pandemic and fertility responses: TFR simulation analysis using parity progressions in South Korea
Volume 49 - Article 32    | Keywords: COVID-19, fertility intentions, marriage intentions, simulation

Variations in male height during the epidemiological transition in Italy: A cointegration approach
Volume 48 - Article 7    | Keywords: cointegration analysis, early life conditions, height, historical demography, infant survival, time series

Leveraging deep neural networks to estimate age-specific mortality from life expectancy at birth
Volume 47 - Article 8    | Keywords: death rates, deep neural network, forecasting, life expectancy

Now-casting Romanian migration into the United Kingdom by using Google Search engine data
Volume 45 - Article 40    | Keywords: Bayesian analysis, Google, international migration, time series, trends