I teach a standard, junior-level, two-semester sequence in probability and mathematical statistics, MATH 335-336, at Oberlin College. In this sequence students learn the mathematical theory that underlies statistical practice as we cover the random variables, functions of random variables, expectation, the central limit theorem, estimators, confidence intervals, hypothesis testing, and regression, among others. Most of the students who take the sequence have no previous experience with statistical applications or with data. Unfortunately, in MATH 335-336 students see little of the applied side of the discipline - there only so much that we can do in two semesters! Although they learn about sampling distributions and large-sample properties of estimators, they learn little about the concerns practicing statisticians have about how samples are actually drawn: experimental design, randomization, bias, etc. I address this problem by offering an additional, one-credit, course - MATH 337 - DATA ANALYSIS - as an adjunct to MATH 336.
The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education