I often counsel activists not to worry overly much about sample sizes. They look small, but the math works out because probabilities of independent events multiply, and the sampling of every respondent is an independent, random event.
But as Ed Morrissey points out, NBC’s new poll really is tiny. The MoE is 10.
I promised last week that Newt Gingrich would get a slot in the next graphic, so here it is. When you finish in second or tied for second in the last two national polls, you’ve earned it.
For the first time in a while though, I can’t really say for sure who’s ahead. I don’t know that the Republicans have a frontrunner right now. Is Herman Cain leading, or Romney? How close is Gingrich? Has Rick Perry faded permanently below the Pauldoza line?
When I write about the polling, I hesitate to say more than I have to about the events going on that drive the numbers. I risk introducing unnecessary bias due to mixing the math with my own observations.
But the Herman Cain harassment story is the story right now. Two new pre-debate polls are out. Cain is down further, Rick Perry is back down after Cain attacked him, so guess who’s on the rise, in second or tied for second in both polls? Newt Gingrich.
First came Cain, then came Politico, then came USA Today/Gallup and NBC News/Wall Street Journal with the latest numbers.
This also make three straight post-scandal polls that have shown Cain to have re-lost his lead over Romney.
It always pleases me when two polls taken close together have very similar results. Even if they make out to be wrong some speculation of mine.
So yes, it’s looking like Herman Cain isn’t exactly being helped this week. And if the new Rasmussen poll is genuinely showing a trend from the previous national poll, then he needs this story done as soon as possible. Eyes are wandering.
Obviously the big story this week in the Republican Presidential race is the story Politico broke discussing sexual harassment allegations, and whether Herman Cain would be helped or hurt by that story.
As it turns out, if the new Quinnipiac poll is to be believed, he was already on the way up before the story broke.
Why yes, I am ignoring the polling of Iowa. It’s conceivable that the polling is accurate and we’re going to see record turnout at the caucuses on the Republican side, records above and beyond the record turnout seen in 2008. But my assumption is that polling caucuses is hard, especially for polling systems designed to predict elections, not caucuses.
Instead I’m checking in with the first national polling in a week, as CBS brings Herman Cain his best news in a while.
There’s plenty of talk about the Republican CNN debate in Nevada, asking who won and who lost. I’ve enjoyed using the polling to make those determinations, because the debates have tended to swing the numbers. But, to know where the swing is, we have to know where we started.
The new Associated Press/GfK/Roper poll helps tell us just that.