Ziyue Tang

I joined the Department of Social Statistics at The University of Manchester in September 2024 as a PhD researcher. My research focuses on understanding, predicting, and mitigating differential participation patterns in longitudinal surveys, with a particular emphasis on addressing non-response and attrition in survey data. By applying advanced statistical techniques, including machine learning and structural equation modelling, my goal is to develop methods that enhance data quality and improve the representativeness of longitudinal studies.

My academic journey reflects a deep interest in using statistical tools to tackle complex social research problems. During my undergraduate studies at Hunan University (2017-2021), I worked with data from the China Family Panel Studies (CFPS) to examine the relationship between household assets and fertility rates. While pursuing my MSc in Digital Innovation in Built Asset Management at UCL (2021-2022), I collected primary data for a project on how environmental policies in office spaces affect employee productivity and well-being. Most recently, during my MSc in Social Research Methods and Statistics at The University of Manchester (2023-2024), I worked with the Understanding Society survey, further refining my skills in managing and analysing complex datasets.

These experiences, from working with established databases to collecting primary data, have deepened my understanding of how data quality and collection methods impact research outcomes. This has driven my focus on improving longitudinal survey practices in my PhD research.

My PhD project is conducted in collaboration with the National Centre for Social Research (NatCen) and focuses on developing prediction models for longitudinal non-response, identifying key subgroups at risk of attrition, and implementing targeted interventions. This partnership allows us to test these methods in real-world data collection settings, contributing to both theoretical advancements and practical improvements in survey methodologies.

Research Interests

My research interests include survey methodology, longitudinal data analysis, non-response prediction, and adaptive survey designs. I am particularly interested in how statistical models can improve data collection practices, ensuring more accurate and representative data in social science research. Additionally, I am more interested in applying machine learning techniques to address real-world challenges related to data quality and demographic behaviour.