National and local population projections with Bayesian hierarchical models
64th ISI World Statistics Congress - Ottawa, Canada
Format: CPS Paper
Keywords: "bayesian, forecasting, population
Session: CPS 23 - Bayesian statistics
Monday 17 July 4 p.m. - 5:25 p.m. (Canada/Eastern)
In this paper we describe a new approach to population projections based on Bayesian hierarchical models and implemented in open source R code.
Time and age (auto-)correlations are incorporated via Gaussian process priors and/or flexible non-linear smooth terms while spatial and social-demographic characteristics are easily included.
This method efficiently solves small area/population issues and allows us to incorporate qualitative and quantitative prior information and even expert assumptions.