"If I were polling to find out how the Hagee endorsement hurt or helped John McCain, I might over sample the Catholic vote."

There are two phases to poll estimation. Phase 1: Estimation of subgroup belief. Phase 2: Estimation of population preference or belief. Subgroups are OFTEN over-sampled, to get a more accurate estimate of the beliefs of that subgroup. However when we form the composite to represent the population as a whole, the results from the subgroup will be weighted to fairly represent their proportion in the population as a whole.

This happens with AA, hispanics, etc. It also happens with Dems and Republicans. Very often, the poll determines if you are a Dem or Rep, and computes a subgroup belief there. Then, the beliefs are weighted to show the population as a whole.

This is one IMPORTANT reason why polls often differ. It is not just the simple sampling difference, where different polls get different results because the people are different. Rather, the sampling weights indicating proportion of population are different. Even the same poll results in hands of different pollsters could result in different conclusions.

That's why I call it a black art. It's not scientific in the standard statistical sense, because you incorporate the population weights, which are also unknown and estimated. The process involves weighting estimates with other weights which are also estimates. Somewhat convoluted.

"he WSJ/MSNBC poll oversampled African Americans. Polls are supposed to represent population percentages of national demographics, yet this poll sampled twice as much of african-americans as populate the US. Since they are going for Obama 9 out of 10, no wonder the stats are skewed."

What an ignorant comment. This exhibits the problem with people commenting when they don't know anything.

The sample size is one thing. Of course they over-sampled blacks. HOWEVER, THE SAMPLING HAS NOTHING TO DO WITH HOW THEY USE THE INFORMATION.

Every poll in the WORLD, EVERY SINGLE ONE, uses sampling weights to weight or express the importance of the value from each individual. That's what they did here, I'm sure.

You say that Barack's church criticized Israel?

Really?

"BEIT SIRA, West Bank — Ali Abu Safia, mayor of this Palestinian village, steers his car up one potholed road, then another, finding each exit blocked by huge concrete chunks placed there by the Israeli Army. On a sleek highway 100 yards away, Israeli cars whiz by.

“They took our land to build this road, and now we can’t even use it,” Mr. Abu Safia says bitterly, pointing to the highway with one hand as he drives with the other. “Israel says it is because of security. But it’s politics.” "

Israel is the new Nazi Germany. They need a serious spanking. The US Government is too cowed by the Jewish lobby to do anything about them. It will take some serious pressure by American patriots to wean us away from Israel. Israel needs A SERIOUS KICK IN THE BUTT. They are a fascist state, and we need to rein them in.

I agree with Barack's church. Why do you back the fascist state of Nazisrael?

"Could she get a salon account? Would be interesting to hear details. Always skeptical of any poll, myself. Maybe because no one ever polls me!"

Her friend, if she actually exists, is not a pollster. Pollsters are a specific type of statistician. Most statisticians don't know diddly about polling - that's me for sure. I'm a statistician, but know only a little about polling. Polling is a black art, not a science. So her friend, if she exists, who is not a pollster, has no special standing to comment anyway.

It's like doctors. You don't see a proctologist about your throat cancer.

are biased.

"And what, pray tell, are the defects of yon poll? The WSJ is highly respected, at least pre-Murdoch, even if one finds the editorial board a little to the right of ones taste? It's not their first poll."

The WSJ poll is the "battleground" poll, with one pollster a Dem, and one a Rep. It's a perfectly fine poll, and all polls are wrong, but some are less wrong.

If you love Hillary, because she is so strong, so fine, such a FIGHTER, then anything that threatens "our girl" is evil, wrong, and of course defective. That's the problem with the poll - it's the wrong message. Polls conducted in pretty much the same way which result in more pro-Hillary results are, of course, better.

Yep, shoot that messenger...

except, of course, it's bad for Clinton-bots.

The poll is fine. It's Hillary that's up to her ass in alligators.

The messages are coming in, and Hillary is going down. The relentless, unfair, biased, and Rovian attacks that Hillary has been launching have back-fired. She is not going to win PA by 20 points, which she must do. If she wins PA at all, it will be by 5 pts, which is a loss.

Remember, in PA, if she wins by LESS than 20 pts, it's a loss.

She must win IN by 20 pts. If she wins IN by less than 20 pts, it's a loss.

I'd feel a little sorry for you Clinton-cultists, but you have been so relentlessly unpleasant that my reservoir of the milk of human kindness is about tapped out.

"Obama is still trying to have it both ways with Rev. "god damn america" Wright. He disagrees with what the good reverend has said on several occasions (the white church is satan, the government created AIDS, america is responsible for 911, etc.) but not enough to leave his church evidently."

He already talked about Wright.

You don't seem very bright. Did you know that Wright is no longer at that church?