Looking at Relationships

Abstract

We think of a dataset as a collection of d-tuples (a d-tuple is an ordered list of d elements). For example, the Chase and Dunner dataset had entries for Gender; Grade; Age; Race; Urban/Rural; School; Goals; Grades; Sports; Looks; and Money (so it consisted of 11-tuples). The previous chapter explored methods to visualize and summarize a set of values obtained by extracting a single element from each tuple. For example, I could visualize the heights or the weights of a population (as in Fig. 1.7). But I could say nothing about the relationship between the height and weight. In this chapter, we will look at methods to visualize and summarize the relationships between pairs of elements of a dataset.