Tutorial: Statistical Presentation Graphics

Frank E Harrell Jr, Dept. of Biostatistics, Vanderbilt University School of Medicine, Nashville, TN, USA, f.harrell@vanderbilt.edu.


Graphical methods are being increasingly used for exploratory data analysis.  Some of the many graphical tools that are useful in this setting are scatterplot matrices, nonparametric smoothers, and tree diagrams.  Statistical graphics for presenting information have been used much longer, but most of the commonly used graphics used in papers, presentations, and the popular media, such as bar charts and pie charts, are either poor or misleading in communicating information to the reader.  This tutorial begins with a series of graphical horror stories from the scientific and lay press.  Then elements of graphical perception and good graph construction, many from the writings of Bill Cleveland, are covered.  Practical suggestions for choosing the best chart or graph type, making good and clear graphics, and formatting are covered.  Techniques for simultaneous presentation of multiple variables are described.  Examples of model presentation graphics will also be given.

The second part of the tutorial consists of interactive demonstrations of how to make effective statistical graphics using the freely available R environment for data analysis and graphics (www.r-project.org).  This will focus on base and lattice graphics as well as graphics functions in the presenter's Hmisc package.  At the close of the workshop some graphical marvels from the literature (especially from Edward Tufte and Howard Wainer) are presented.