ABSTRACT
Chapter 2 focuses on exploratory data analysis, which must precede any application of multivariate statistical techniques. This is an important step to identify descriptive parameters, such as mean and standard deviation, the assumptions’ verification, among which we highlight normality, homoscedasticity, and data linearity as well as data pattern, especially the existence of outliers and missing data. Initially, the chapter presents the concepts of central and dispersion measures, such as mean, median, mode, range, variance, and standard deviation, followed by an illustrative example. In the sequence are the concepts of normality, homoscedasticity, and linearity, their respective tests and results, and implications and remedies when these assumptions are not achieved – and finally, the tests to identify outliers and missing data, with instructions about how to deal with these later patterns. The chapter also includes exercises, such as a road map to perform the analysis, an interpretative exercise with results tables, and a market context to guide a research design.
