Try to Untangle This Knot of Numbers
Two of my usually-favorite sources for information and insight (AAPOR and the New York Times) came together this week with an embarrassing, face-scrunching example of convoluted statistical reporting:
But Internet use correlates inversely with age and voting habits, making [online polling] a more severe problem in predicting elections. While all but 3 percent of those ages 18 to 29 use the Internet, they made up just 13 percent of the 2014 electorate, according to the exit poll conducted by Edison Research. Some 40 percent of those 65 and older do not use the Internet, but they made up 22 percent of voters.
This was written in an op-ed piece in the New York Times by a past president of AAPOR (the American Association for Public Opinion Research) and current professor of public policy and political science at Rutgers.
I struggle to make sense of it. Each time I try to simplify and rephrase, I get stuck on statistics that do a poor job supporting the story. Is he trying to say that online polls are risky because people who vote in elections are not online? If so, he needs better data, because the numbers he gives support that claim only indirectly. It reminds me of a quote from Edward Tufte, an expert on how to communicate quantitative data:
If the statistics are boring, then you’ve got the wrong numbers. Finding the right numbers requires as much specialized skill—statistical skill—and hard work as creating a beautiful design or covering a complex news story.
And I’ll add to that: If the statistics are confusing, then you’ve got the wrong numbers.
A reader (or a client) should never have to scratch her head and try to re-phrase our narratives into a sensible and compelling story. That’s our job, and it takes as much expertise as the statistical work behind it. That expertise of turning data into stories is still less common than we might hope.