Currently working as a Statistics Leader at the Statistics and Data Science Innovation Hub at GSK.
Experience in many therapeutic areas, including cardiovascular, metabolic and infectious diseases using a wide range of methods (joint models, dynamic predictions, mixed-models, survival analysis, multi-state models).
For the past few years I have also been providing scientific and regulatory advice as a part-time methodological assessor at CBG-MEB, which is part of the European regulatory medicines network.
In the past I worked at the Erasmus University Medical Center as a PhD candidate and later as a post-doctoral researcher. During my years at Erasmus MC, I worked on the development of novel methodology with a focus on joint models for longitudinal & time-to-event data. More specifically, during the course of my PhD at the Department of Biostatistics and the Department of Thorax Surgery at the Erasmus University Medical Center I worked on the development of joint models that can incorporate intermediate events (such as treatment changes, side-effects etc.) and time-varying treatments during follow-up as well as the development of individualized dynamic prediction tools which are adaptive to future changes regarding the occurrence of intermediate events or/and treatment changes. This work was done under the supervision of Prof. Dimitris Rizopoulos, Prof. Johanna J. M. Takkenberg and Dr. Mostafa M. Mokhles.
PhD in Biostatistics, 2021
Erasmus University Medical Center
MSc in Statistics, 2015
BSc in Statistics & Actuarial Science, 2011
Univeristy of Piraeus
The package JMbayes2 fits joint models for longitudinal and time-to-event data. It can accommodate multiple longitudinal outcomes of different type (e.g., continuous, dichotomous, ordinal, counts), and assuming different distributions, i.e., Gaussian, Student’s-t, Gamma, Beta, unit Lindley, censored Normal, Binomial, Poisson, Negative Binomial, and Beta-Binomial. For the event time process, right, left and interval censored data can be handled, while competing risks and multi-state processes are also covered.
JMbayes2 fits joint models using Markov chain Monte Carlo algorithms implemented in C++. Besides the main modeling function, the package also provides a number of functions to summarize and visualize the results.
“ Random words of wisdom in curly quotes ”
rQuote is an R-package that I developed while trying to teach myself how to develop R-packages. Doing so allowed me to practice the extensive online book on R-package development by Hadley Wickham and to learn how to create a website for my package using pkgdown. On the same time I was able to learn some web-scraping with rvest and improve my regex skills. It also made this whole process fun and creative. Most importantly, though, I got to read many random quotes. Too many random quotes. Definitely more than I should.
You can download my full CV here: CV
(Last Update: 24/02/2022)