Data Visualisation

This chapter describes approaches to visually representing the data. We explain the importance and use of visualisations, and the uses and procedures to generate some commonly used graphs and charts. We begin with explaining bar charts in detail, from generating a simple bar chart, displaying frequencies on the bars, filling in the bars with colours, giving chart and axes titles. We then discuss clustered bar charts, alongside displaying and positioning the legend to identify bars for each of the categories. Following this, we explain stacked bar charts, both by frequencies and by percentages. We then explain pie chart and how they differ from bar charts. All the charts/graphs are explained in the context of measurement scales used for quantifying data. We continue with our discussion on the line graphs for showing trend and seasonality. We then proceed to explain the use of scatter plot. Normal distribution is one of the key assumptions of parametric tests. We explain histogram with probability density curve and box plots for examining normality. We end the chapter by giving an overview of the ggplot2 package and demonstrate generating a bar chart.