Dr Menelaos Pavlou

* @ucl.ac.uk

Biographical Details 

I am an Associate Professor in Medical Statistics at the Department of Statistical Science since April 2019. I am also leading a Mentoring and Support program for Postgraduate Teaching Assistants. I collaborate with the National Institute of Cardiovascular Outcomes Research (NICOR), where I am part-based, and I provide statistical oversight of the analytical team.

I completed a degree of Mathematics in 2004 at the Aristotle’s University of Thessaloniki, Greece, followed by an MSc in Statistics (2005) at the Department of Statistical Science, UCL. After having worked for a consulting company, I pursued a part-time PhD in Medical Statistics in the Department of Statistical Science, UCL (2007), while working as a Medical Statistician at the Centre of Sexual Health and HIV Research, UCL. I was awarded with a PhD in 2012, and until 2016 I was employed as a post-doctoral research associate in the Department of Statistical Science, UCL. 

Research Interests

I am interested and currently working on topics in the following areas:

• Risk Prediction Modelling
• Prediction-oriented variable selection in low-dimensional settings
• Penalised Regression method (Ridge, Lasso etc.)
• Comparison of Institutional Performance and Detection of Outliers
• Analysis of Clustered Data and Informative cluster size
• Missing data

I also have an interest in software development (e.g., see R package ‘sampsizeval’ for sample size calculations for validation of risk models).

Prospective PhD students

If you are interested to have a PhD related to the topics above, contact me at m.pavlou@ucl.ac.uk for an informal discussion. Keep an eye for departmental teaching assistantships and other funding opportunities here, and please get in touch well before the deadline to discuss/develop your research proposal.

Selected publications

• Pavlou M, Qu C, Omar RZ, Seaman SR, Steyerberg EW, White IR, Ambler G (2021). Estimation of required sample size for external validation of risk models for binary outcomes. Statistical Methods in Medical Research. doi:10.1177/09622802211007522.
• Pavlou M, Ambler G, Seaman SR, De Iorio M, Omar RZ (2015). Review and evaluation of penalised regression methods for risk prediction in datasets with few events, Statistics in Medicine, doi: 10.1002/sim.6782.
• Pavlou M, Ambler G, Seaman SR, Guttman O, Elliott P, Omar RZ (2015). How to develop a more accurate risk prediction model when there are few events, BMJ, 351:h3868.
• Pavlou M, Ambler G, Seaman SR, Omar RZ (2015). A note on obtaining correct marginal predictions from a random intercepts model for binary outcomes, BMC, Medical Research Methodology, 15:59, doi: 10.1186/s12874-015-0046-6.
• O'Mahony C, Jichi F, Pavlou M, Monserrat L et al. (2013). A novel clinical risk prediction model for sudden cardiac death in hypertrophic cardiomyopathy, European Heart Journal, doi:10.1093/eurheartj /eht439.