I think he is hinting at this when he writes here:
For a variety of reasons, the Rasmussen Reports daily Presidential Tracking Poll is less volatile than some other polls and always shows a somewhat smaller convention bounce than reported by others. This is primarily because we weight our results by party identification (see methodology). Looking at the data before adjusting for partisan identification, the Republican convention appears to have created a larger surge in party identification than the Democratic convention the week before. If this lasts, it could have a significant impact on Election 2008.
Excellent post.
That’s exactly what I’m saying. Rasmussen is a more conservative approach (I mean slower, less volatile...not referring to political conservative.)
However, above all else, Rasmussen is very open about his special sauce. Others don’t reveal theirs. I think it makes sense to be more conservative.
Someone who thought he was democrat last week and suddenly thinks he’s Republican this week makes me wonder what he’ll think next month. That’s why I like a 90 day rolling average to balance all that out.