A CRITICAL-LOOK AT SOME ANALYSES OF MAJOR-LEAGUE BASEBALL SALARIES

At a data analysis exposition sponsored by the Section on Statistical Graphics of the ASA in 1988, 15 groups of statisticians analyzed the s ame data about salaries of major league baseball players. By examining what they did, what worked, and what failed, we can begin to learn ab out the relative strengths and weaknesses of different approaches to a nalyzing data. The data are rich in difficulties. They require reexpre ssion, contain errors and outliers, and exhibit nonlinear relationship s. They thus pose a realistic challenge to the variety of data analysi s techniques used. The analysis groups chose a wide range of model-fit ting methods, including regression, principal components, factor analy sis, time series, and CART. We thus have an effective framework for co mparing these approaches so that we can learn more about them. Our exa mination shows that approaches commonly identified with Exploratory Da ta Analysis are substantially more effective at revealing the underlyi ng patterns in the data and at building parsimonious, understandable m odels that fit the data well. We also find that common data displays, when applied carefully, are often sufficient for even complex analyses such as this.