Affordable Access

Access to the full text

Introducing hat graphs

Authors
  • Witt, Jessica K.1
  • 1 Colorado State University, Department of Psychology, Fort Collins, CO, 80523, USA , Fort Collins (United States)
Type
Published Article
Journal
Cognitive Research: Principles and Implications
Publisher
Springer International Publishing
Publication Date
Aug 14, 2019
Volume
4
Issue
1
Identifiers
DOI: 10.1186/s41235-019-0182-3
Source
Springer Nature
Keywords
License
Green

Abstract

Visualizing data through graphs can be an effective way to communicate one’s results. A ubiquitous graph and common technique to communicate behavioral data is the bar graph. The bar graph was first invented in 1786 and little has changed in its format. Here, a replacement for the bar graph is proposed. The new format, called a hat graph, maintains some of the critical features of the bar graph such as its discrete elements, but eliminates redundancies that are problematic when the baseline is not at zero. Hat graphs also include design elements based on Gestalt principles of grouping and graph design principles. The effectiveness of the hat graph was tested in five empirical studies. Participants were nearly 40% faster to find and identify the condition that led to the biggest difference from baseline to final test when the data were plotted with hat graphs than with bar graphs. Participants were also more sensitive to the magnitude of an effect plotted with a hat graph compared with a bar graph that was restricted to having its baseline at zero. The recommendation is to use hat graphs when plotting data from discrete categories.

Report this publication

Statistics

Seen <100 times