Summary
I am currently on a five-year MRC Career Development Award fellowship working on a project titled 'Towards realistic methods for evaluating public health interventions using time-series data'. Previously, I was a Senior Research Associate (2020-2024) and Investigator Statistician (2016-2020) for the Population Health theme led by Daniela De Angelis. Prior to joining the MRC Biostatistics Unit, I completed my PhD on ‘Point process modelling of coordinate-based neuroimaging meta-analysis’ at the Department of Statistics, University of Warwick, under the supervision of Thomas E Nichols. I did my MSc and BSc in Statistics in Athens, where I come from. I also serve (since 2025) as an Associate Editor for the Journal of the Royal Statistical Society Series A.
Research Interests
My main area of research is Bayesian causal inference. More specifically, I develop methods for evaluating complex interventions using time-series observational data, and apply those to substantive public health problems. My current work explores the problems of effect heterogeneity, unobserved confounding and spatial interference. Most of the applications I currently collaborate on are in the field of Hepatitis C virus. More broadly, I am interested in developing Bayesian hierarchical and multivariate models to tackle problems in Biostatistics.
Selected papers
- Samartsidis et al (2024). A Bayesian multivariate factor analysis model for causal inference using time-series observational data on mixed outcomes. Biostatistics 25 (3): 867-884.
- Seaman et al (2022). Nowcasting COVID-19 deaths in England by age and region. Journal of the Royal Statistical Society Series C (Applied Statistics) 71 (5): 1266-1281.
- Samartsidis et al (2020). A Bayesian multivariate factor analysis model for evaluating an intervention using observational time-series data on multiple outcomes. Journal of the Royal Statistical Society Series A (Statistics in Society) 183 (4):1437-1459.
- Samartsidis et al (2019). Assessing the causal effect of binary interventions from observational panel data with few treated units. Statistical Science 34 (3): 486-503.
