Shao, Zejing; (2025) Evaluating the Impact of Universal Credit on Mental Health Using Quasi-Experimental Designs within a Bayesian Hierarchical Framework. Doctoral thesis (Ph.D), UCL (University College London).

Preview

Text Thesis_final_ZejingShao_.pdf - Submitted Version Download (3MB) | Preview

Abstract

Evaluating the impact of policies in non-randomised settings is fundamental to applied analyses in epidemiology and econometrics. Recent evidence suggested that deteriorating mental health in the UK may be linked to policy changes, notably the introduction of Universal Credit. This welfare reform, implemented over the past decade, has had significant effects on public health outcomes. This study aimed to investigate the impact of Universal Credit on mental health among UK residents using robust statistical methods. Employing a quasi-experimental design, I enhanced the difference-in-differences (DiD) analysis within a Bayesian hierarchical framework to account for spatial and temporal effects in longitudinal data. To address the challenges of non-representative sampling and typical weighting issues, I integrated the analysis into a Multilevel Regression and Poststratification context. Ultimately, this approach developed a Bayesian hierarchical framework for a DiD analysis that evaluates the effects of Universal Credit on mental health at the small-area level, effectively handling spatial and temporal dependencies and overcoming limitations associated with traditional approaches in longitudinal data studies.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item