Statistics is a vital field in modern science, providing tools and techniques for extracting meaningful insights from vast amounts of data. In recognition of the contributions of exceptional statisticians, the Centre for Translational Medicine awards a monthly “Statistician of the month” award. This month’s winner is Péter Mátrai, a talented statistician whose work has contributed to the development of innovative methods for analyzing complex biomedical data. In this interview, we had the pleasure of speaking with Péter about his background, research, and the importance of statistics in translational medicine. Join us as we learn more about the fascinating work of this month’s award winner.
What are the roles of a statistician?
The statistician has to be involved from the planning phase throughout the whole research process until the publication of the results. It is very limited what you can do in the analysis if the experimental design was not carefully planned. Ronald Fisher, the famous statistician phrased it this way: “to consult the statistician after an experiment is finished is often merely to ask him to conduct a post mortem examination. He can perhaps say what the experiment died of “.
What do you think is the most important thing for a statistician to remember when working with data?
The most important thing is to know and understand the process of how that specific data that you are working with is generated. What is the population from which the sample was drawn? How was the sample chosen? When, where and how were the measurements carried out? There are a lot of aspects of the data generation process and they all have to be clear for the statistician to choose the appropriate method and interpret the results the right way.
How often do you update your skills and knowledge as a statistician?
Constantly, there is no other way, as this is a rapidly evolving field. Fortunately, statisticians are always ready to help their colleagues with math, methods, explanations, coding, etc. so we learn from each other a lot. Wherever I worked as a statistician, national statistical office, pharmaceutical industry, university, I always had the experience that colleagues are very helpful and they like sharing their knowledge.
There is a lot of data to analyse, which may seem monotonous to an outsider. How would you stay motivated during this process?
Yes, it can be monotonous, however many times there is a way to automatize the monotonous processes by writing a code that does the unwanted job for you. If I have a boring task I motivate myself with thoughts such as “ok, this is boring now but someone else needs my job done to finish his/her project” or “yes, I don’t like doing this now but I need to do it to have tasks later that I like more”.