Thursday, May 28, 2009

Were Chrysler Dealerships Closed Based on Politics?

Two days ago, Dave Burris of DelawarePolitics took note of an alarming statistic:
Doug Ross points out that there is a heavy correlation between big Republican donors and which Chrysler dealers got their licenses yanked. Very interesting.
Dave came back today with a followup link to this post, which quotes a lawyer for several of the dealers. Dave presents it as blockbuster news:
Doug Ross blows the doors off of any doubt that the Chrysler shutterings were politically-motivated. Welcome to DealerGate.
Ross reviews the relative merits of closing several dealers, and concludes that the odds against closing just five particular dealers is "one ten-millionth of one percent." Now I defy any serious student of statistical analysis to find a text that shows how a sample of five cases can yield such a high level of confidence.
Also left out of these calculations is any reference to a control group. How many car dealers overall donate to Republicans, and how many to Democrats? Without that number, the "heavy correlation" is meaningless.
Nate Silver of FiveThirtyEight
does the math:

Overall, 88 percent of the contributions from car dealers went to Republican candidates and just 12 percent to Democratic candidates. By comparison, the list of dealers on Doug Ross's list (which I haven't vetted, but I assume is fine) gave 92 percent of their money to Republicans -- not really a significant difference.

There's no conspiracy here, folks -- just some bad math.

So an alarming inference vanishes in the face of a straightforward statistical comparison. Come on guys, do your homework.


Post a Comment

<< Home