Article Text
Abstract
This workshop is an introduction to the principles of good graph and table design as pioneered by Cleveland [1] and Tufte [2] and updated by Few [3] so that the participant can better answer the following questions:
Which of the messages in my research results requires a graph or table?Recognizing how graphs improve on simple statistics and convey much more information. Knowing when a table is better, or keeping the data in the body text.
How can I best convey the message?Striving for clear vision by choice of graph, scaling, discrimination of data series, minimizing non-data ink, avoiding chart junk.Striving for clear understanding through a balance between data and explanation. Using order, subheadings, formatting and rules to guide your reader through your table data.
Is my graph/table truthful?Creating a direct proportion between graph and data quantities, avoiding forms prone to misinterpretation, labels to prevent ambiguity; keeping data in context, avoiding more dimensions in the graph than in the data.
References
-
Cleveland WS. The elements of graphing data: Hobart Press, Summit, NJ, U.S.A.; 1994.
-
Tufte E. The visual display of quantitative information. 2nd ed: Graphics Press, Cheshire, CT, U.S.A.; 2001.
-
Few S. Show me the numbers. Designing tables and graphs to enlighten. Analytics Press, Oakland, CA, U.S.A.; 2004.
Disclosure of Interest None declared
DOI 10.1136/annrheumdis-2014-eular.6161