ABSTRACT
In this short chapter and the following three longer chapters (Chapters 10, 11, and 12) we will be concerned with multivariate data. Such data arise when researchers measure several variables on each individual in their study, and where all variables need to be examined simultaneously in order both to uncover whatever “patterns” or “structure” the data may contain and understand the key features of the data. All the variables in a multivariate data set are random variables, unlike in the regression models of Chapter 3 to 8, where only the response variable is considered to be a random variable. The analysis of multivariate data, multivariate analysis, is essentially a collection of techniques, many largely descriptive rather than inferential, that have in common the aim to display or extract any “signal” in the data in the presence of noise and, in a very general sense, to discover what the data may be trying to tell us.
