ABSTRACT
The topics covered include core topics in probability and statistics that are central to the analysis of sports data. This chapter considers some more advanced methods that build on these core topics. When comparing results from different years, it is often appropriate to adjust for the different scoring environments; however, there may be too much variability in the yearly scoring averages to use them directly in the adjustments. The information provided by the summary function when applied to the output from glm is similar to the information provided when applying summary to the output from lm. For example, the parameter estimates are given under the Estimate heading and the standard error of the estimate is given under Std. Error. An alternative to using regression techniques for modeling the relationship between a response variable and a large set of predictors, particularly when there are many possible interactions, is to use tree-based methods.
