Often the very best method to explain, explore, and summarize a set of numbers–a very large set–is to look at images of those amounts. Graphics visually display data by using points, lines, a coordinate system, numbers, symbols, phrases, shading, and color.
The goal of information visualization is to establish the key features of this data and to guide in selecting the proper statistical techniques. Moreover, visualization processes help in spotting errors and unusual values in the data enabling corrective actions to be taken early in the analysis.
Theorists such as Edward Tufte have defined the requirements for the attainment of excellence in statistical graphics. induce the viewer to think about the substance rather than about methodology, graphic design, or the technology of picture production; encourage the eye to compare different pieces of information; disclose the information at several levels of detail, from a broad overview of the fine structure; function a reasonably clear purpose: description, exploration, tabulation, or decoration; Until recently, chart design for data analysis and presentation was mostly unscientific.
William Cleveland and Robert McGill applied theory to a graphic understanding with their study which analyzed the relative precision with which various graphical forms conveyed qualitative information. Their results revealed that when images are”read,” position decisions about specific graphic elements such as bars in a bar chart and lines on a line graph were more precise than angle and length judgments like those made when seeing pieces of a pie in a pie graph.
Their decisions called for a dismissal of a few of the more popular chart forms–bar graphs, split bar graphs, pie graphs, and statistical maps with shading–in favor of dot graphs, scatter charts with the group, and framed-rectangle graphs. Cleveland explains the very important link between chart and visual perception. When a chart is created, qualitative and categorical information is encrypted, then the information is visually perceived. Some graphical methods contribute to efficient, precise transmission, while others lead to ineffective, inaccurate perceptions of this information.