Statistical Data Science: a thriving future

Data Science is the twin discipline that marries hard-core computing fields, such as data bases, visualization and numerical computation, with statistical or machine learning methodology. This marriage came about with the advent of high-throughput sensing and large data storage technologies. As the resulting revolution was in large part driven by technology, the methodological inductive side lacked behind and has only recently started to catch up.

In this talk I will focus on three challenges that this presents us. (i) How do we make use of Data Science to make scientific progress?  By connecting data and detailed mathematical modelling more intensively through high-dimensional inference and statistical network science, I believe that great progress can be made. I will show several examples. (ii) How do we educate a new breed of data scientists to be able to face future challenges and to avoid Small Data problems in Big Data? In my opinion, a thriving Masters programme that combines high-end computing & machine data handling, mathematical modelling and inductive statistical reasoning, is a way to make a mark in the data science landscape.  (iii) Finally, how do we embed data science strategically into the evolving scientific, bureaucratic and societal landscape? This needs to be a multi-pronged approach; we need to take our fate in our own hands by strategic collaborations to show off the enormous power of data science to a wider audience, by proactive national and international networks of data scientists to gain visibility and show common purpose and by lobbying important stakeholders of the importance of data science.

Professor Ernst C. Wit is the head of Mathematics (19 FTE) at the University of Groningen in the Netherlands. He obtained PhDs in Philosophy (1997) and Statistics (2000) in the US. From 2000 until 2005 he was in the Statistics Department at the University of Glasgow, where he became a Reader. In 2005 he became head of the Medical Statistics Unit (12 FTE) at the University of Lancaster as full professor and as Director implemented a thriving Master in Statistics programme. Since 2008 Wit is at the University of Groningen, where he has continued to work on methodological development in high-dimensional inference with a specific focus on network modelling. He is the author of 105 peer-reviewed publications. He has served as the President of the European Bernoulli Society and as member of the Board of Directors of the International Biometrics Society. He is currently President of the Dutch Biostatistics Society. He is a founding member of the Data Science and Systems Complexity Center (DSSC), which also established a Data Science Master and a Statistics and Big Data Master programme, which he leads. He is currently presiding over a European COST Action, entitled COSTNET (CA15109), that deals with novel methods for statistical network science and that brings together 250 groups in Europe. He advises the Ministry of Internal Affairs in the Netherlands on statistical matters relating to elections and referendums since 2014