Eric-Jan Wagenmakers - Statistical pitfalls in cognitive neuroscience

In this talk I discuss three common statistical errors that are particularly relevant for cognitive neuroscience. The first error concerns the fact that the difference between "significant" and "not significant" is itself not necessarily significant. The second error concerns the overinterpretation of 2 x 2 interactions that do not cross. The third error is perhaps most serious, and it concerns the presentation of exploratory studies as confirmatory. To avoid these statistical pitfalls, the field requires new methods and procedures, several of which will be discussed in detail.