On the (ab)use of statistics in the legal case against the nurse Lucia de B

We discuss the statistics involved in the legal case of the nurse Lucia de B. in The Netherlands, 2003-2004. Lucia de B. witnessed an unusually high number of incidents during her shifts, and the question arose as to whether this could be attributed to chance. We discuss and criticise the statistical analysis of Henk Elffers, a statistician who was asked by the prosecutor to write a statistical report on the issue. We discuss several other possibilities for statistical analysis. Our main point is that several statistical models exist, leading to very different predictions, or perhaps different answers to different questions. There is no such thing as a `best' statistical analysis.