ABSTRACT
This chapter knows how to describe a sample of data in terms of descriptive statistics (the sample mean, sample variance, etc.). The aim of inferential statistics is therefore to draw conclusions about the possible values of the population properties (parameters) that might plausibly have given us our sample properties (statistics). The chapter distinguishes between the descriptive statistics that characterize our sample (which we know), and the corresponding parameters that characterize the population (to which we wish to generalize). Many statistical tests involve estimating the properties of the population(s) from which our data are drawn, assuming that the populations are normally distributed. The commonest modern approach is a form of resampling known as ‘bootstrapping’, which can be used to test hypotheses, or calculate confidence intervals on statistics (such as the mode or median) for which other tests are too complicated, or non-robust.
