Abstract
SummaryGraphical methods such as colour shading and animation, which are widely available, can be very effective in communicating uncertainty. In particular, the idea of a ‘density strip’ provides a conceptually simple representation of a distribution and this is explored in a variety of settings, including a comparison of means, regression and models for contingency tables. Animation is also a very useful device for exploring uncertainty and this is explored particularly in the context of flexible models, expressed in curves and surfaces whose structure is of particular interest. Animation can further provide a helpful mechanism for exploring data in several dimensions. This is explored in the simple but very important setting of spatiotemporal data.
Highlights
In 2010, the Royal Statistical Society launched a 10-year statistical literacy campaign with a discussion paper by Wild et al (2011) on making statistical concepts accessible
It is stating the obvious to say that graphical methods play a very important role in both the communication of statistical information and concepts in a manner which is largely free of technical language
Examples include exploratory data analysis (Tukey, 1977), the careful visual design expressed in lattice graphics (Sarkar, 2008) and the animation and interaction provided by systems such as XLispStat (Tierney, 1988), ggobi (Cook and Swayne, 2007) and Mondriaan (Theus and Urbanek, 2008)
Summary
In 2010, the Royal Statistical Society launched a 10-year statistical literacy campaign with a discussion paper by Wild et al (2011) on making statistical concepts accessible. There are general tools for enabling user interaction, provided for example in systems such as Shiny (Chang et al, 2016) Despite this array of tools, the standard approaches to graphical display remain those based on relatively simple point and line drawings, such as histograms, boxplots, bar charts and scatter plots, supplemented occasionally by colour filling. An example is provided by Jackson (2008) who introduced the concept of a density strip to represent distributions by the simple device of a bar of colour whose intensity is proportional to the density function at each location This produces a visually appealing display whose continuous gradations match well with the intuition of what uncertainty means. Animation (a) illustrates the unpredictable nature of sampled observations and the accumulation of the ‘footprints’ of the data into a density strip representation of a density estimate whereas (b) shows several distributions in density strip form and (c) shows density strips constructed from data on aircraft speed, on a log-scale, for three different time periods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of the Royal Statistical Society Series A: Statistics in Society
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
