Rasmussen SUNDAY Poll

Rasmussen Reports ^

[KQQL]

Election 2004

Presidential Ballot

Bush 47.6%
Kerry 46.4%
Other 2.6%
Not Sure 3.4%
RasmussenReports.com

BOUNCE IS OVER: PER FREEREPUBLIC FAVORITE POLLSTER

[ableChair]

Lets wait until Gallup and IBD have their new polls out later next week -

Agreed, and my primary point in all this, but I don't see why my post confused you. You keep asserting that the Reps are oversampled. Just because they used more Reps than Dems does not necessarily mean Reps were oversampled. It's good that you like facts, so let me try to explain it with a specific example, as opposed to a general thesis. Suppose Reps lie about their choice more often than Dems - JUST SUPPOSE - and suppose that Newsweek KNOWS this from historical data. Lets also suppose Newsweek KNOWS what value to ascribe to this dishonesty phenomenon. Then it is NOT the case that they have oversampled JUST because they called more Reps. Remember, that's just one example. There could be any number of factors like that. But the point is that YOU don't know what they are, Newsweek does. So you can't legitimately do what you're trying to do, that is, make assumptions without all the relevant information. By delving into the internals of something you really know nothing about you're just tripping over yourself.

[uscabjd]

I read sometime ago that Reps and Inds who trend Rep is 45%. Same with Dem and Inds who trend Dem. That is why the country is so evenly divided in elections, and why the true Undecided % is so small. Am I wrong?

[okstate]

CNN can't report Rasmussen because they use automated polling, and CNN isn't allowed to report any polls that use automation. That's why you never hear them talk about Rasmussen or SurveyUSA.

[Chieftain]

Ahh, I see. I learned something new today. Thank you!

[okstate]

"The Newsweek breakdown was 37D-31R (or close to that a fellow freeper dealing with polls showed) "


Newsweek actually had a sample of 38R-31D-31I

Republicans were oversampled 2-3 points, Dems undersampled about 5-6 and Independents oversampled 3-5 points

[okstate]

Yeah, I thought it was interesting. I don't remember where I read that, though..

[zook]

Rasmussen came out of W.B. Doner Co., an ad agency in Detroit, the same one that spawned Cathy Guisewhite (sp?), the cartoonist. Rasmussen uses automated polling. His sample doesn't include cell phones. By polling on a holiday weekend, he is most likely undersampling Republicans, who are more likely to be away from home.

[zook]

Only in your own mind. He's "popular" in the sense that people visit his site and he polls every day. But he's by no means anyone's favorite pollster, except his own.

[COEXERJ145]

FREEREPUBLIC FAVORITE POLLSTER

Only in your mind.

[KQQL]

Party ID Bush Kerry Und
Republican 38% 94 4 2
Democrat 31% 14 82 4
Independent 31% 45 40 15
Total 100% 52 41

Party ID Bush Kerry Und
Republican 35% 94 4 2
Democrat 38% 14 82 4
Independent 27% 45 40 15
Total 100% 50 43 6

newsweek poll

[KQQL]

it was in 2000.

LOL

and still is quoted here more often than other pollsters

[RightWhale]

Is there something wrong with this poll? It hasn't changed for a year.

[hawaiian]

What does Rasmussen know? His 2000 night-before-the-election poll showed Bush with a 49-40 lead over Gore. He has no credibility.

[southernnorthcarolina]

Rasmussen's outfit at the time, Portrait of America, had Bush beating Gore, the day before the election, by 9 points... I believe he had it at 49% - 40%

I hadn't focused on the POA -- Rasmussen connection. Very interesting. He bombs out one year, and changes names.

That's very reminiscent of the strategy of football prognosticators. Pick up any pre-season college football or NFL magazine (Street and Smith's, for example), and you'll see page after page of advertisements for betting services which will, for a stiff fee, provide you the names of "sure winners" for each week of the upcoming season. And most of these services (Vegas Hotline, or Coach's Guaranteed Picks, or Pigskin Pro, to make up a few names) will brag about their track records from previous seasons. But of course, those with low success ratios don't take out ads (at least not under the same name) the next year.

[POA2]

Agreed, and my primary point in all this, but I don't see why my post confused you. You keep asserting that the Reps are oversampled. Just because they used more Reps than Dems does not necessarily mean Reps were oversampled. It's good that you like facts, so let me try to explain it with a specific example, as opposed to a general thesis. Suppose Reps lie about their choice more often than Dems - JUST SUPPOSE - and suppose that Newsweek KNOWS this from historical data. Lets also suppose Newsweek KNOWS what value to ascribe to this dishonesty phenomenon. Then it is NOT the case that they have oversampled JUST because they called more Reps. Remember, that's just one example. There could be any number of factors like that. But the point is that YOU don't know what they are, Newsweek does. So you can't legitimately do what you're trying to do, that is, make assumptions without all the relevant information. By delving into the internals of something you really know nothing about you're just tripping over yourself.

I don't agree with your premise here at all - First off, the fact is NewsWeek has a "history" that needs to be looked at - You cannot just look at the this Newsweek poll in a vacuum - Historically NewsWeek polls are junk - They jump all over the place for whatever purpose NewsWeek wants them to serve -

Secondly I would offer you some words of wisdom from Thomas Sowell (brilliant man) - "there is nothing more complex then avoiding the obvious" -

And that is exactly what you are trying to do here - The obvious fact is Republicans we're well oversampled and Dem's were well UNdersampled in the latest NewsWeek poll - This is what clearly brought about the 11pt lead for GWB! -

If a more accurate weigthing was applied GWB would not have an 11pt lead - It would be closer to 5pt - (that is the facts) -

I don't care what agenda or purpose NewsWeek wants to have for under or over sampling - facts remain facts -

ANd lastly we need to wait until both IBD and Gallup come out with polls to see where this race stands.

[bIlluminati]

Let me tell you all how a scientific poll would sample respondents. Rasmussen is mostly right, partly wrong.

Say about 75% of registered voters are party-affiliated likely voters, with a 39%D and 36% R, with a likelihood of voting of 85%. The other 25% are independents, with a probability of voting of 40%. To get the best results with the fewest calls, you want to under-sample the 75% and oversample the 25%. Why? What we're measuring here is sensitivity, changes, and only a few voters move from Party A to Party B, or vice versa, on a daily basis. But a voter may go from a 20% voter to an 80% voter..

Next, people lie. If you ask them how likely they are to vote, they will overstate. So you also look at actual data from previous elections. Note: these may be contaminated with vote fraud, probability approaching 100% in some precincts. E.g. city of Philadelphia reports 98% of all those over 18 registered. E.g. net vote fraud in 2000 Presidential election favored Gore by about 4,000,000 votes, 240,000 in Florida. However, therefore, polling should reflect expected vote fraud. Rasmussen in 2000 was new enough he didn't do it, and got disrespected for counting actual respondents without weighting for fraud.

Yes, once you use weighting, it's easy to manipulate the results. That's why the 2008 elections are important, to keep the 2010 census honest. We should take a tip from the Israelis of 2,010 years ago, and all live in rural areas (Idaho is best) on 1 April 2010. HHOS (ha-ha, only series).

And when you break the numbers down this way, it's still clear that turnout is key. Supposedly, conservative Christians didn't go to the polls in 2000 because of the DUI thing. I suspect that they did go, but in urban districts their votes went uncounted, thus explaining why more ballots are spoiled in urban than suburban precincts.

Finally, in Oregon and Washington, many to all votes are mailed in. Note how Senator Packwood was pushed to resign in Oregon just in time for vote-by-mail to take effect. Note that this is the method of voting that Stalin used in the 1920s to gain power. He said "It doesn't matter who votes. It only matters who counts the votes."

PS In the final analysis, the Second Amendment trumps the First.

[ableChair]

And lastly we need to wait until both IBD and Gallup come out with polls to see where this race stands

We're in violent agreement on that, as we both already posted. As for your argument, you're just going in circles. Your basic theme is that facts don't matter so you'll just assume whatever you want to get the result you want. I see an agenda here.
Thanks for your reply, your logic is now deconstructed thusly:
You outright deny that it is possible for there to be ANY legitimate reason whatsoever for Newsweek to weigh numbers based on information outside YOUR ken. Manifestly absurd.

QED

Oh, BTW, speaking of ignoring the obvious, do you really think that Newsweek pollsters, even with all their lackluster intellectual merit and bias, are too stupid to see the problem you identified by comparing the face value of two numbers?

[hershey]

Gee, if these figures are correct, why is Kerry firing everyone right and left? Things seem to be pretty much on track. Everything hunky dory except for MamaT.'s little tummy upset. Why all the panicky stories in print, the complaints that Kerry's not doing what's needed? But how can he when he's busy arranging deck chairs on the Titanic.