Column: Lies and Statistics
The other day, I posted a link to a New York Times story from June on the Fish Wrap’s Facebook page. The story presented every county in the United States along with some various statistical evidence to go along with the Times’ theory that, many areas of the nation are doing better than others in this latest post-recession recovery.
Their numbers, when all computed together, placed Polk County as 2,595 out of 3,135 counties in the United States. All the numbers can be found by going to http://tinyurl. com/kcvf5hm, which will take you to the Times’ story.
Another interesting note in all of this is the No. 1 ranking for the top county in the United States: Los Alamos County, N.M. They reached the top spot due largely to the high number of college graduates and workers with masters and doctoral degrees.
The story takes a lot of different statistics to calculate the ranks, from the number of graduates with high degrees to how many people in the community are on disability. Here’s my biggest problem with this story and all based on statistics: when were the numbers generated?
Not once did the writers of this story mention when these numbers were compiled, or even how they were generated. How is one to truly understand where we are today if we’re using numbers that might be older than Christmas, or fresh from some latest study released in the New England Journal of Medicine?
In my opinion, without that context it’s hard to make comparisons. It also makes us all too easily manipulated by those statistics and how they are presented.
I think one of the comments left on the story hit the nail right on the head too: what is their definition of easy or hard?
It’s particularly hard to think about this – or any story involving statistics – as being patently honest considering people believe just about any statistic they want to in the end.
I read about a survey on Bloomberg News just last week that hit the nail right on the hammer with my argument. Results of a survey conducted by by U.K. pollster Ipsos Mori found that Americans rank just above Italians in their understanding of statistics.
These results claim Americans believe 15 percent of the population identifies themselves as Muslim. In reality, only 1 percent of the population identifies themselves as followers of Islam.
Then there’s my favorite of the lot, that goes to show we all watch too much television if this response is to be believed.
“What percentage of American girls aged between 15 and 19 years give birth each year?” Survey says: 24 percent. In reality, its only 3.1 percent.
Then again, when were the “true” answer survey results compiled? Once again, that seems to have been left out of the story.
Also an interesting sidenote about this, only 11,527 people were interviewed in the poll over- all. Which means they based the thoughts of an entire set of countries off what would be a molecular sized amount of people in the giant pool of the human population.
Polling data for politics works the same way, and so the smallest number of people compared to the overall voting population ends up telling our nation’s leaders what to think and how to vote. It tells cable news companies what to think voters will do in elections.
In an age when data matters more than ever – from all those mathematical calculations used by the computer just to type this column to the billions of phone calls being scooped up by the NSA daily – not telling the entire truth with statistics is sinful.
If we can’t even get the numbers of what we are right, then what’s the point of reporting them, much less relying on them as a gauge to define who and what we are.
Statistics are important, but only if used in an honest and straightforward way. We rely on data too heavily in decision making, mainly in response to what we see as a short term numerical problems.
We also need to shame those who seek to manipulate statistics for their own gain. Those charlatans of calculation deserve ridicule for their reckless abuse of the numbers.
What we forget is that all the data in the world is great, but relying on it too heavily forces us to become too focused on the trees to see the whole forest. There’s the bigger picture, the individual and the force of interconnectedness driving our world today just as much as the numbers. If we remember that, we’ll use that data to make better decisions overall.