All too often, the mainstream media looks solely at the toplines of polls. They tend to ignore the all-important demographic breakdown of the crosstabs to determine what they really mean.
Thus, the breakdowns I like to provide for my readers.
Now previously I've mentioned my questions regarding potential sampling problems with Quinnipiac and Rasmussen. Both tended to oversample to benefit Democrats in their polls of Ohio races.
[Click here for my Rasmussen questions back in May, and here for my questions about Quinnipiac]
Well, finally the Columbus Dispatch has decided to take a closer look at the latest Rasmussen poll that showed Rob Portman up by four on Lee Fisher, and they come to the same conclusion:
Rasmussen's explanation of the party ID crosstabs hardly seems to lead to a 4-point Portman lead, unless its sample is overwhelmingly Democratic:
"Portman, a former congressman and George W. Bush administration official, has support from 85% of Republicans, while Fisher is backed by 69% of Democrats. Portman leads by 20 points among voters not affiliated with either major political party."
As mentioned in my links above, this is hardly a new issue. I'm just glad to see the media is starting to take a more substantive approach to reporting on polls.