Article Text

Download PDFPDF
Graphics and statistics for cardiology: comparing categorical and continuous variables
  1. Kenneth Rice1,
  2. Thomas Lumley2
  1. 1Department of Biostatistics, University of Washington, Seattle, Washington, USA
  2. 2Department of Statistics, University of Auckland, Auckland, New Zealand
  1. Correspondence to Dr Kenneth Rice, Department of Biostatistics, University of Washington, Seattle, Washington 98107, USA; kenrice{at}


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.

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.