Graphics and statistics for cardiology: comparing categorical and continuous variables

Abstract

Graphs are a standard tool for succinctly describing data, and play a crucial role supporting statistical analyses of that data. However, all too often, graphical display of data in submitted manuscripts is either inappropriate for the task at hand or poorly executed, requiring revision prior to publication. To assist authors, in this paper, we present several forms of graph, for data typically seen in Heart, including dot charts, violin plots, histograms and boxplots for quantitative data, and mosaic plots and bar charts for categorical data. Justification for using these specific plots is drawn from the literature on visual perception; we also provide software instruction and examples, using various popular packages.