My acquaintance Louis Nick recently put a link up on Google+ to, a site which ranks the fifty United States by a subjectively defined definition of “freedom”. Now, the first thing I wonder when I see a list like this is, what does it correlate with? Specifically, how does “freedom” correlate with income?

Here’s a scatterplot of median family income (data from Wikipedia, which cites “2010 United States Census and the 2006-2010 American Community Survey 5-Year Estimates”) versus “freedom index” (i.e. position on the above site’s list, so low numbers correspond to highest “freedom”).


If I were a libertarian, it seems to me I would expect to see a correlation between income and “freedom”. But in fact my hypothesis was that there would be an anticorrelation. The truth seems to be there’s little relationship at all. A fit to a straight line would have positive slope, I’d say, but would be a poor characterization of the data.

One way to spin it would be to observe that of the 10 “least free” states 8 are above the US median family income ($62,982); the latter group includes 2 of the 3 highest income states (Maryland and New Jersey) while the third highest (Connecticut) just barely misses being included. (On the other hand the remaining 2 are among the  3 lowest income states: Mississippi and West Virginia). Meanwhile of the 10 “most free” states 7 are below the median.

But an obvious rejoinder is that —I think — these are before-tax incomes. My guess is that after taxes, this plot would look even flatter.

No, I think if you want to advance a thesis that greater freedom generates greater economic well-being — or lesser — then these data do not do much to help your case. A libertarian can point to New Hampshire and Virginia as an illustration that “freedom” can coexist with wealth, but they (and Maryland, New Jersey, Mississippi, and West Virginia) are outliers here.




2 thoughts on “Correlations

  1. Of course, you have to recognize that the 50 states share a huge set of free and unfree factors inherited from the federal government. It’s like doing pendulum experiments on a moving train (a real one, not an idealized one). You need to widen the range of inputs. See, for example, an international comparison at


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s