Statistical methods for estimating population size
Project description
Estimating population size is a common problem in statistics with many well-established methods. However, these methods rely on strict assumptions about the structure of the population. These assumptions are often unrealistic and may result in faulty population estimates. Methodology to estimate population size is commonly applied to epidemic and ecological data sets, but is being increasingly applied to social good applications, estimating the number of individuals facing human rights abuses (Silverman, 2020).
The project will advance methods for estimating population size, for example, by including population dynamics, or by stratifying the population into subgroups. The project will exploit advancements in Bayesian computation and functional data analysis to develop novel and efficient computational algorithms, this will allow for new models to be successfully implemented.
This project will be jointly supervised with Dr Rowland Seymour (Rights Lab, UoN)
Project published references
Bird, S. M., & King, R. (2018). Multiple Systems Estimation (or capture-recapture estimation) to inform public policy. Annual Review of Statistics and Its Application, 5, 95–118. https://doi.org/10.1146/annurev-statistics-031017-100641
Otis, D. L., Burnham, K. P., White, G. C., & Anderson, D. R. (1978). Statistical Inference from Capture Data on Closed Animal Populations. Wildlife Monographs, 62, 3–135. http://www.jstor.org/stable/3830650
Silverman, B. W. (2020). Multiple‐systems analysis for the quantification of modern slavery: classical and Bayesian approaches. Journal of the Royal Statistical Society. Series A, (Statistics in Society), 183(3), 691–736. https://doi.org/10.1111/rssa.12505
More information
Full details of our Maths PhD
How to apply to the University of Nottingham