December 28, 2011, 5:45 pm By NATE SILVER
I’m not always a big fan of dissecting individual polls — mostly because there are liable to be a plethora of them in Iowa and New Hampshire over the next several days and their errors will tend to be mitigated as more are added to the average.
Nevertheless, the new CNN poll of Iowa contains a methodological quirk that is worth bringing to your attention and which will probably result in the survey underestimating the support for Ron Paul.
The issue is that CNN’s Iowa poll was conducted by using a list of registered Republican voters and registered Republicans only: