Statistical graphics

Statistical graphics, also known as graphical techniques, are information graphics in the field of statistics used to visualize quantitative data.

Overview

Whereas statistics and data analysis procedures generally yield their output in numeric or tabular form, graphical techniques allow such results to be displayed in some sort of pictorial form. They include plots such as scatter plots, histograms, probability plots, spaghetti plots, residual plots, box plots, block plots and biplots.

Exploratory data analysis (EDA) relies heavily on such techniques. They can also provide insight into a data set to help with testing assumptions, model selection and regression model validation, estimator selection, relationship identification, factor effect determination, and outlier detection. In addition, the choice of appropriate statistical graphics can provide a convincing means of communicating the underlying message that is present in the data to others.

Graphical statistical methods have four objectives:

• The exploration of the content of a data set
• The use to find structure in data
• Checking assumptions in statistical models
• Communicate the results of an analysis.

If one is not using statistical graphics, then one is forfeiting insight into one or more aspects of the underlying structure of the data.

History

Statistical graphics have been central to the development of science and date to the earliest attempts to analyse data. Many familiar forms, including bivariate plots, statistical maps, bar charts, and coordinate paper were used in the 18th century. Statistical graphics developed through attention to four problems:

• Spatial organization in the 17th and 18th century
• Discrete comparison in the 18th and early 19th century
• Continuous distribution in the 19th century and
• Multivariate distribution and correlation in the late 19th and 20th century.

Since the 1970s statistical graphics have been re-emerging as an important analytic tool with the revitalisation of computer graphics and related technologies.

Examples

William Playfair's trade-balance time-series chart, published in his Commercial and Political Atlas, 1786

John Snow's Cholera map in dot style, 1854.

Famous graphics were designed by:

• William Playfair who published what could be called the first pie chart and, in 1796, the well known diagram that depicts the evolution of England's imports and exports.
• Florence Nightingale, who used statistical graphics to persuade the British Government to improve army hygiene,
• John Snow who plotted deaths from cholera in London in 1854 to detect the source of the disease, and
• Charles Joseph Minard who designed a large portfolio of maps of which the one depicting Napoleon's campaign in Russia is the best known.

A special type of statistical graphic are the so-called isotypes. These are graphical tools designed by Otto Neurath with the specific purpose of achieving changes in society through visual education of the masses.

See also

• Data Presentation Architecture
• List of graphical methods
• Visual inspection

References

Attribution

 This article incorporates public domain material from websites or documents of the National Institute of Standards and Technology.

Further reading

• W.S. Cleveland (1993). Visualizing Data. Summit, NJ, USA: Hobart Press. ISBN 0-9634884-0-6. 
• W.S. Cleveland (1994). The Elements of Graphing Data. Summit, NJ, USA: Hobart Press. ISBN 0-9634884-1-4. 
• Paul J. Lewi (2006). Speaking of Graphics. 
• Edward R.Tufte (2001) [1983]. The Visual Display of Quantitative Information (2nd Edition ed.). Cheshire, CT, USA: Graphics Press. ISBN 0-9613921-4-2. 
• Edward R. Tufte (1992) [1990]. Envisioning Information. Cheshire, CT, USA: Graphics Press. ISBN 0-9613921-1-8. 

External links

• Trend Compass
• Alphabetic gallery of graphical techniques
• DataScope a website devoted to data visualization and statistical graphics