The problem with using so many statistical graphics in the press: we do not know how to interpret them correctly

The problem with using so many statistical graphics in the press: we do not know how to interpret them correctly

Using a data graph, of any type, a priori would allow us to better understand a statistic, a comparison, or even the severity of a problem. A picture is worth a thousand words, it is often said. And people read less and less. The problem is that our educational system has not caught up, and the common reader may not be able to interpret many graphs.

A recent Pew Research Center study, in fact, suggests that only half of the Americans surveyed could correctly interpret a simple scatterplot . A scatter plot or scatter plot or bubble chart ball chart is a type of mathematical diagram that uses Cartesian coordinates to display the values ​​of two variables for a data set.

No college degree, worse

In particular, people without a college degree are substantially less likely to be able to draw correct conclusions from the graph.

Analytics G759001654 640

The study actually stated that 63%, not 50%, of the respondents could read the graph. But this statement was based on the fact that 63% had answered correctly to an answer among four possible options: 25% would have been able to do it completely at random , even if no one could have read the graph.

Added to all this is another problem, as explained by Carl Bergstrom and Jevin West , professors at the University of Washington, in their recent book Bullshit: Against Quackery :

Although the data visualization may seem objective, the designer has a great deal of control over the message that he wants to convey with the graphic. Even using accurate data, a designer can manipulate the way that data will make us feel. You can create the illusion of a correlation, even if none exists, or make a small difference between two variables appear very large.