Research in the Social Statistics pathway investigates social dynamics in space and time, focussing on ageing and ethnicity in Manchester, population dynamics in Liverpool, and methodological research in criminology and health sciences in Lancaster.

Programmes eligible for NWSSDTP funding

The list below includes all Master’s programmes that are eligible for NWSSDTP funding and the typical PhD programmes that are supported under this pathway. Other PhD programmes within these universities may be considered – please reach out to the relevant Pathway Representative (see contact details below) or the NWSSDTP Office if the PhD programme you are interested in is not listed here. Please note that the NWSSDTP does not fund standalone Master’s programmes – these can only be funded as part of a Master’s + PhD Studentship.

Lancaster University

• MSc Criminal Justice and Social Research Methods
• MSc Criminology and Social Research Methods
• MSc Social Research
• PhD Applied Social Statistics
• PhD Sociology
• PhD Statistics and Epidemiology

University of Liverpool

• MSc Geographic Data Science
• PhD Geography

University of Manchester

• MSc Social Research Methods and Statistics
• MSc Social Network Analysis
• PhD Social Statistics

For information on how to apply for funding, please visit our How to Apply page.

Pathway Representatives

Contact details for Social Statistics Pathway Representatives can be found here: https://nwssdtp.ac.uk/about/contact-us/pathway-leads/

Current Social Statistics Pathway Students and Alumni

Estimation of Quality-Adjusted Life-Years via Joint Longitudinal-Survival Modelling

Cost-effectiveness analyses are key in allocating healthcare resources. The health outcomes used for these analyses should incorporate the impact of a treatment on both the length of life and health-related quality of life (HQoL). The quality-adjusted life-year (QALY) is one such summary measure. An area under the curve (AUC) method can be used to estimate QALYs, through linear interpolation of the longitudinal HQoL data points. However, summary measures such as the AUC may result in biased estimates. We aim to investigate whether and when using joint longitudinal-survival models can reduce this bias, and lead to efficiency gains when estimating QALYs.

---

Understanding, Predicting and Mitigating Differential Patterns in Longitudinal Surveys

This project aims to develop innovative solutions to address non-response in longitudinal surveys. By leveraging machine learning models and adaptive data collection designs, the research will enhance the quality of longitudinal data, reducing bias and improving participation rate.

---

An holistic statistical approach for determining the relationships between social, economic and health markers using the English Longitudinal Study of Ageing

The global elderly population is expected to double by 2050, reaching nearly 2.1 billion. Initiatives to tackle this elderly population inflation are needed in order to sustain society’s well-being and people’s quality of life. We develop methodology aiming to understand the dynamics of the ageing process and the relationships between the factors that affect ageing progression (evidence from the English Longitudinal Study of Ageing).

---

Developing synthetic data methods for administrative databases

The aim of the project is to develop synthetic data methods that are capable of handling large administrative databases, with particular focus on the synthesis of categorical variables. Effective synthetic data methods could provide analysts with access to administrative data, whilst protecting the confidentiality of the individuals included.

---

Modelling and forecasting the spatial and temporal patterns of bilateral international migration flows

While migration flow data are available from individual countries of South America, they often incomplete and/or incomparable between countries and over time. Thus, there is a need to use different data sources for estimating South American migration flows. However, data sources differ. In order to overcome these differences and the limitations of each data source, my research generalises the Raymer et al.’s model (2013), which enables the combination of various data sources through a measurement model that corrects for data inadequacies. The resulting outcome will be a set of synthetic annual estimates of migration flows with measures of uncertainty for South American countries from 1990 to 2018.

---