I like to call myself data engineer. It is a way for me to mix my engineer degree in Physics with my degree in Biostatistics. I like to take a problem and to bring a practical solution. I like the machine learning approaches which I found very powerful and have high potential for solving practical challenges in data analysis. But I try to not forget that this is essentially re-branding of statistical methods.
I yell at people who said “Statistics can be made to prove anything …”. Unfortunately, statistics are used much like a drunk man uses a lamppost: for support, not illumination. I invest a lot of time developing tools for data visualisation and try to communicate them. In my work, I try to convince clients and collaborators that more than 50% of a statistician job is actually to try to represent data … and the modelling/inference part comes after.
Beside statistics, I believe that wikipedia is one of the most impressive collective effort of the Humanity. I am a big fan of github. To ease the pressure, I like to do rock climbing, squash, yoga and running.
I am a PhD student at Zurich University in the applied statistics group. My research interests includes Multivariate and Bayesian analysis, systems epidemiology analysis, software developments and open research. After working several years in clinical research at different positions, I decided to enhance my education in Physics by doing a master degree in Biostatistics at Zurich University. Then I continue my education in statistics with a PhD in epidemiology and biostatistics. Beside my research activities, I am the maintainer of the statistical consulting service for the members of the Faculty of Science of the UZH.
Full digital CV.
PhD in Biostatistics, 2019
MSc in Biostatistics, 2015
MSc in Physics, 2010
BSc in Physics, 2009
R packages for statistical computing/data engineering
– maintainer and author of varrank R package that perform variable selection with applications in systemic datasets
– maintainer and author of abn R package that models multivariate data with Additive Bayesian Networks
– contributor of ATR R package for plotting party trees in left-right orientation instead of the classical top-down layout
29 March 2019, co-organizer of a workshop on Multivariate analysis using Additive Bayesian Networks. (Utrecht, Netherland)
7⁄9 May 2019, co-organizer of a ECVPH Residents workshop on ABN modeling. (Zurich, Switzerland)
6⁄7 February 2019, 2 full days lecture (including hands-on sessions) on regression models, mixed models and and introduction to ggplot (with attention to plotting caveats in exploratory data analysis) at the advanced statistics workshop: Good scientific practice for Neuroscientists using R programming language. (Zurich, Switzerland)
4 December 2018, co-organizer of the 1st Causality workshop talk, Bayesian Networks meet Observational data. (UZH, Switzerland)
20 November 2018, Research in Progress talk. Additive Bayesian Network modeling applied to patient preference surveys. (UZH, Switzerland)
4 October 2018, talk in Nutricia (Danone). Multivariable analysis: variable and model selection in system epidemiology. (Utrecht, Netherland)
14 September 2018, M-14E Current topics of Laboratory Animal Science, lecture. Academical statistical consulting service for veterinary research and case study about ethic and statistics. (UZH, Switzerland)
2-3 July 2018, BAYSM 2018, Warwick. Poster: Comparison between Suitable Priors for Additive Bayesian Networks. (Warwick, UK)
30 May 2018. Brown Bag Seminar in ZHAW. Presentation: Bayesian Networks Learning in a Nutshell. (Winterthur, Switzerland)
02 May 2018. Institute of Global Health, Geneva. Presentation: Advances in Additive Bayesian Network applied to observational systems epidemiology datasets. (Geneva, Switzerland)
21-23 March 2018. Society for Veterinary Epidemiology and Preventive Medicine (SVEPM), Tallinn. Poster: Information-Theoretic Scoring Rules to Learn Additive Bayesian Network Applied to Epidemiology. (Tallinn, Estonia)
24-26 July 2017. TIES GRASPA, Bergamo. Poster: Additive Bayesian Network approach applied to time series and longitudinal datasets. (Bergamo, Italy)