SAS: Visualizing Change: An Innovation In Time-Series Analysis
Posted: 1 November 2007
The paths that our lives take and the speed of passage from one place to the next are difficult to retrace. The story of a life is a story of change as one navigates, in the present, what immediately becomes the past and is mostly forgotten. Wouldn’t it be enlightening if your life could be revealed as a picture, a map that displayed your entire journey on a single page, a record of the many intersections, turns, paths, and events that have become lost in the haze of fallible memory? On the pages that follow I examine this problem of tracing change through time, not in terms of our personal journeys, but in terms of the journeys that reside in our data. Those of us who work with information, striving to uncover and understand the stories it has to tell about our businesses or what’s happening in the world, struggle to bring these stories to light.
“Visual representations of data take advantage of the unique ability of visual perception to detect meaningful patterns that might otherwise remain hidden.”
I spend my days helping people make sense of data and then present to others what they find using visualization techniques. Visual representations of data take advantage of the unique ability of visual perception to detect meaningful patterns that might otherwise remain hidden. Even highly skilled statisticians recognize when it makes sense to clear their heads of statistics and simply use their eyes to explore data. John Tukey, renowned Princeton statistician and author of Exploratory Data Analysis, recognized the important role of our eyes in the analytical process. He wrote:
The basic intent of data analysis is simply stated: to seek through a body of data for interesting relationships and information and to exhibit the results in such a way as to make them recognizable to the data analyzer and recordable for posterity.
A picture is not merely worth a thousand words, it is much more likely to be scrutinized than words are to be read. Wisely used, graphical representation can be extremely effective in making large amounts of certain kinds of numerical information rapidly available to people.
One great virtue of good graphical representation is that it can serve to display clearly and effectively a message carried by quantities whose calculation or observation is far from simple.
(John W. Tukey, The Collected Works of John W. Tukey. Belmont, CA: Wadsworth Inc., 1988)
Since Tukey penned these words, a great deal of attention has been given in academic circles to visual means for exploring and making sense of data. As they have learned more and more about visual perception—how it works and how it can be applied to data analysis—they have developed tools that exploit this potential.