Accuracy of Local Authority Population Forecasts Produced by a New Minimal Data Model: A Case Study of England

Philip Rees () and Tom Wilson ()
Additional contact information
Philip Rees: University of Leeds
Tom Wilson: The University of Melbourne

Population Research and Policy Review, 2023, vol. 42, issue 6, No 8, 30 pages

Abstract: Abstract The preparation of forecasts for small and local area populations involves many challenges. Standard cohort-component models are problematic because of small numbers, which make estimation of rates unreliable. Because of this, the Synthetic Migration Population Projection (SYMPOPP) model was designed to forecast local populations without need for detailed area-specific information. This model had been used successfully for small area forecasts in Australia. The objective of the paper is to assess its performance when applied to local areas in England. The model uses a bi-regional structure based on a movement population account. Sub-models of total population change are employed to control future change. Fertility, mortality and migration rates are borrowed from national statistics, constrained to small area indicators. The model uses an Excel workbook with VBA routines and is relatively easy and quick to use. Model inputs were calibrated for 2006–2011 and used to forecast for 2011–2021. Results were tested against the census-based 2021 mid-year populations. A new error statistic, Age Structure Error, was used to evaluate Basic and Refined model versions against official projections. The two versions of SYMPOPP posted lower errors. The simple models had fewer areas with errors of 10% or more (12.3–12.6%) compared with the official projections (14.5% of areas). Investigation revealed that these errors occurred in local authorities with high military, student, prison, or ethnic minority populations, influenced by factors not captured in a projection model for the general population.

Keywords: Population forecasts; Simple models; Cohort-component models; Age Structure Errors; Forecast performance (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11113-023-09839-2 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:poprpr:v:42:y:2023:i:6:d:10.1007_s11113-023-09839-2

Ordering information: This journal article can be ordered from
http://www.springer. ... es/journal/11113/PS2

DOI: 10.1007/s11113-023-09839-2

Access Statistics for this article

Population Research and Policy Review is currently edited by D.A. Swanson

More articles in Population Research and Policy Review from Springer, Southern Demographic Association (SDA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().