The analysis of national mortality trends is critically dependent on the quality of the population, exposures and deaths data that underpin death rates. We develop a framework that allows us to assess data reliability and identify anomalies, illustrated, by way of example, using England & Wales (EW) population data. First, we propose a set of graphical diagnostics that help to pinpoint anomalies. Second, we develop a simple Bayesian model that allows us to quantify objectively the size of any anomalies. Two-dimensional graphical diagnostics and modelling techniques are shown to improve significantly our ability to identify and quantify anomalies. An important conclusion is that significant anomalies in population data can often be linked to uneven patterns of births in cohorts born in the distant past. In the case of EW, errors of more than 9% in the estimated size of some birth cohorts can be attributed to an uneven pattern of births. We propose methods that can use births data to improve estimates of the underlying population exposures. Finally, we consider the impact of anomalies on mortality forecasts and annuity values, and find significant impacts for some cohorts. Our methodology has general applicability to other population data sources, such as the Human Mortality Database.
|Number of pages||31|
|Journal||Journal of the Royal Statistical Society Series A: Statistics in Society|
|Early online date||25 Jan 2016|
|Publication status||Published - Oct 2016|
FingerprintDive into the research topics of 'Phantoms Never Die: Living with Unreliable Population Data'. Together they form a unique fingerprint.
- School of Mathematical & Computer Sciences - Professor
- Research Centres and Themes, Centre for Finance & Investment - Professor
- School of Mathematical & Computer Sciences, Actuarial Mathematics & Statistics - Professor
Person: Academic (Research & Teaching)