Why the empirical sciences need statistics so desperately

Paper in proceeding, 2013

Science can be described as a systematic attempt to extract r eliable infor- mation about the world. The cognitive capacities of homo sapiens come with various biases, such as our tendencies (a) to detect patterns in what is actually just noise, and (b) to be overly confident in our conclusions. Thus, the scien tific method needs to involve safeguards against drawing incorrect conclusions due to su ch biases. A crucial part of the necessary toolbox is the theory of statistical inference. There exists a large and well-developed (but of course incom plete) body of such theory, which, however, researchers across practically all of the e mpirical sciences do not have sufficient access to. The lack of statistical knowledge there fore forms a serious bottleneck in the quest for reliable scientific advances. As has been obs erved by several authors in recent years, statistical malpractice is widespread acros s a broad spectrum of disciplines, including (but not limited to) medicine, cognitive science s, Earth sciences and social sciences. Here I will first try to describe the overall situation and pro vide some concrete exam- ples, and then move on to discuss the more difficult issue of wha t can and needs to be done