Answers are grounded in this paper and cite their sources.
Research reveals how different graph types influence data understanding, based on 2000 evaluations.
People do not read surface charts and segmented bar graphs correctly-correct interpretations run as low as 15 per cent. There are other types of graphs that can be used. Decisions on what type to use should depend on what the reader is expected to get from the presentation. Such decisions should depend not only on what the message is, but also on the complexity of the material to be presented. Objective research evidence from about 2000 persons provides the basis for such conclusions. The research summarized dealt with the question of whether or not data could be effectively presented graphically, as well as with selection of graphs to best serve specific purposes. The graph types discussed are used both to convey the findings of the research and to illustrate the relative merits of each type.
No takes yet. Share an insight, caveat, or question.
Richard C. Powers (1966) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: