Prestige lecture by Prof. Rens van de Schoot at Optentia, Nort-West University, South-Africa

Ho or not Ho, that is the question: How to learn something positive from your data

Half in jest, I start with a story about a black bear to illustrate the current state of affairs of how statistics are used in scientific articles. While doing this, I show that there are some major discrepancies between the formal use of the these statistical tools and the way they are used in practice. Then, I tell a story about Aristotle’s scientific investigations into the shape of the earth in the context of evaluating hypotheses. I conclude that Aristotle was not really interested in testing the classical null hypothesis `The earth is not round´. I show that he was actually interested in evaluating informative hypotheses `The Earth is flat versus the Earth is round´. As I will show with some real life examples, in contemporary science the situation is not much different. That is, many researchers have no particular interest in the traditional null hypothesis. I argue that more can be learned from data by evaluating specific expectations, or so-called informative hypotheses, than by testing the null hypothesis. All criticisms of classical null hypothesis testing aside, the best argument for evaluating informative hypotheses is that many researchers want to evaluate their expectations directly, but have been unable to do so because the statistical tools were not yet available. As I illustrate, these tools are ready to be used for any researcher within the social sciences. In this lecture I challenge the audience to move beyond classical null hypothesis testing, which was the dominant research tool of the 20th century, and together we will move towards the new statistics of the 21th century!