Chapter 13. Fundamental graphical methods

 

In this chapter and the next, I want to shift my attention: I’ll now largely take gnuplot for granted, and concentrate on applying it to problems. Nevertheless, whenever appropriate, I’ll take the opportunity to show you how a certain effect can be achieved with gnuplot. In this chapter I want to talk more generally about different graphical methods and the kinds of problems they’re applicable to. In the next chapter, I’m going to take a number of different problems and walk you through the different steps that the analysis may take. If you will, this chapter introduces la technique, while the next chapter explains la méthode (with a nod to Jacques Pépin).

When faced with a new data set, there are two questions that usually dominate. The first one is, how does one quantity depend on some other quantity—how does y vary with x? The second question (for data sets that include some form of statistical noise) asks, how is some quantity distributed—what’s the character of its randomness? We’ll look at graphical methods suitable for either question in the next two sections. In the last two sections of this chapter, I’ll discuss two particularly challenging problems: ranked data, and methods applicable to large, unstructured, multivariate data sets.

13.1. Relationships

13.2. Counting statistics

13.3. Ranked data

13.4. Multivariate data

13.5. Summary