On using ARIMA model confidence intervals applied to population projections based on the components of change : a case study for the world population

This paper shows how measures of uncertainty from a standard time series model (ARIMA) can be applied to an existing population projection based on components of change using the world as a case study. The measures of forecast uncertainty are relatively easy to calculate and meet several important criteria used by demographers who routinely generate population forecasts. This paper applies the uncertainty measures to a world population forecast based on the Cohort-Component Method. This approach links the probabilistic world forecast uncertainty to the fundamental demographic equation, the cornerstone of demographic theory, which is an important consideration in developing accurate forecasts. The results are compared to the Bayesian probabilistic world forecast developed by the United Nations and found to be similar but show more uncertainty. The results are followed by a discussion suggesting that this new method is well-suited for developing probabilistic world, national, and sub-national population forecasts.