Binary Logistic, the Dutch, and Chocolate

I thought this story was interesting because it illustrates that something that seems difficult like odds ratios (which appears as Exp(B) in the results) can make for an interesting article.  Explaining what we do is at least as difficult as the analysis. "A 50 percent lower risk of death" was a .5 odds ratio is someone's output somewhere.  Although not Exp(B)s, the chart showing cocoa content was a nice touch.  In any case, it is a nice example of a real study, written up for a general readership. http://www.msnbc.msn.com/id/11596575/

It is fun to compare it to the short version of the original.  Also well written, but for another type of reader. http://archinte.ama-assn.org/cgi/content/short/166/4/411  You will find the .5 along with a CI in this short piece.