03-13-2017 07:55 AM
While preparing the geo-analytics examples for the Introduction to SAS Visual Analytics book, I found that many tornados labeled for Kansas, Alabama, and other parts of the United States were plotted in the Atlantic Ocean. How could this be?
The United States National Climatic Data Center website contains US storm events (such as tornadoes, thunderstorms) since 1950. The data set contains the estimated starting location for the tornado along with its estimated strength.
You can build a custom geographic data item if you have the latitude and longitude available. You might recall from elementary school when you studied the globe and learned how it was divided by imaginary parallel lines that circle the globe from and east to west (called latitude) and from north to south (called longitude). When you provide a location’s latitude and longitude, you are referencing these lines. In this dataset, the tornado's starting location is expressed as latitude and longitude.
Some of you might be clever enough to know that Kansas is what most might consider the center of the United States. While not in the center, Alabama is on the North American continent.
When plotting the data, SAS Visual Analytics dutifully represents the data points as indicated. So if someone mistyped a value, then your heartland tornado may appear sea-bound. A simple correction to the latitude or longitude can resolve the issue.
Join my co-authors and me at SAS Global Forum as we present SAS® Visual Analytics Tricks We Learned from Reading Hundreds of SAS® Community Posts. This paper combines our favorite tips from the book and some other ones that we think are worth sharing.