ABSTRACT
The analysis of any data set generally involves a series of steps, the first of which is most often the calculation of a number of relevant summary statistics and the construction of a well-chosen graph. The aim of this step is to aid the researcher in understanding the general characteristics of the data and perhaps to identify any unusual observations or any ‘patterns’ in the data that may need to be considered later when more complex statistical procedures might be applied to the data. Which graphs and which summary statistics are most appropriate for a data set will depend to a great extent on the level of measurement of the observations. The main distinction will be between
continuous
(or quasi continuous) measurements and those that are
nominal
or
categorical
(see Altman, 1991, for a full discussion of scale types).
