The Gap Between Statistics Education and Statistical Practice

The teaching of statistics has evolved more slowly than statistical practice. In diagnosing the problem with undergraduate statistics education, Cobb returns to Leo Breiman’s “two cultures” article and makes some important points. I completely agree with him when, consistently with Breiman’s earlier sentiment, Cobb warns against ceding to others “all methods of analysis that do not rely on a probability model.” Tukey’s profoundly important emphasis on the distinction between exploratory and confirmatory (inferential) methods, including the corruption of operating characteristics due to exploratory preprocessing, remains central to modern statistics. Furthermore, Cobb rightly suggests that computation should play a big role throughout the curriculum.