ABSTRACT
This chapter introduces the use of R in summarizing nominal, ordinal and numeric data by means of ungrouped and grouped frequency distributions for one and two-sample scenarios. Computational methods for traditional univariate summary statistics are then demonstrated, from scratch and through the use of R functions. In addition to typical measures of central tendency, spread and position, the computation of the two measures of shape, skewness and kurtosis, are demonstrated through R functions and by way of basic code. The chapter closes with discussions and demonstrations of two versions of the five-number-summary, the typically encountered one seen in traditional elementary statistics courses and the one that is attributed to Tukey. Included in this discussion is a presentation of using the five-number-summary as a robust means of flagging outliers in data.
