Rasmussen SUNDAY Poll

And you keep thinking it is "how many they called" - They weighted it for a turn-out model that isn't close to any REAL turnout model....What don't you get about that??

Would you like the names and phone numbers? Or do you just not believe them? Well, you can deny the facts, but they're there. As for the number called, that was in fact your argument. See your own previous posts. And if you're arguing that they weighted the phone calls based on a model, that now tasks you with debunking that model. Your argument was that there was NO legitimate reason to weigh the phone calls, remember? Nice attempt to change the argument, but I'm not falling for it. Again, it is incumbent upon you to show:
Normalization was not used
AND/OR the normalization (in this case, the models to which you refer) was invalid.
Have at it, save the rant.

A recent story from another thread:

As CrushKerry observed, GOP respondents outweighed Democratic respondents in the poll, 374 to 303. With 300 Independents noted,that works out to 38.3% Republicans, 31.0% Democrats, and 30.7% Independents of the 977 total from the three. But the Newsweek poll states that 1,188 respondents were polled, with 1,088 Registered voters. And while the press release takes 20 pages to print and read, Newsweek doesn’t say, exactly, how those remaining 111 to 211 respondents breakdown. Also, I took the time to break down the respondents’ percentages: If the Rep/Dem/Ind response was unweighted, Bush would have led Kerry in the poll 58.0% to 42.0%, a sixteen-point lead, not eleven. So, while they don’t say exactly how they weighted their poll, Newsweek did weight the poll to balance things more towards the Democrats. In other words, you should consider deeper issues before accepting or rejecting a statement, whether it’s news you dislike, or news you do like.

Note the reference to "we don't know how Newsweek weighted their poll". Exactly what I've been pointing out. You don't know all the details of the weighting so guesses about what their poll really should be is pointless.

Yet more from Rasmussen - an admission of error:
September 6, 2004--We have been flooded with e-mails asking (in varying tones of politeness) why our poll results seem different from those released by Time and Newsweek.
There are two basic explanations, one involving our polling data and one involving the newsmagazines. For those who need to know the answer before the explanation, the bottom line is that the President is ahead by 4 to 5 points at this time. That's a significant improvement over the past few weeks, but not a double digit lead.
Our current poll (showing the President ahead by just over a point) includes a Saturday sample that is way out of synch with all the days before it and with the Sunday data that followed. In fact, Saturday's one-day sample showed a big day for Kerry while all the days surrounding it showed a decent lead for the President.
It seems likely that Saturday reflects a rogue sample (especially since it was over a holiday weekend). But, it remains in our 3-day rolling average for one more day (Tuesday's report). If we drop the Saturday sample from our data, Bush is currently ahead by about 4 percentage points in the Rasmussen Reports Tracking Poll.

Perhaps this explains Newsweek and Time's choice of normalization? Looks like all the contradictions may lie in faults of the Rasmussen poll -- the Saturday confound.

You've been proven a fool - Gallup numbers out - And they are EXACTLY where I said they would be - Between 5 and 7pts -....NOT 11pts - (too funny) -

But keep spinning that Newsweek polls are accurate - You are too much - Newsweek polls are JUNK - They are not done for accuracy they are done for news stories!! ( J.L.R - If you really know people in the bizz....you'll know who that is....and finally get a clue I know more about Newsweek then you ever will) -

But seriously, you are too funnny - (keep calling).

Note the reference to "we don't know how Newsweek weighted their poll". Exactly what I've been pointing out. You don't know all the details of the weighting so guesses about what their poll really should be is pointless.

If you would simply go to the link I gave you - They have broke down the internals of the NewsWeek poll...and they do have the weighted MODEL Newsweek used - But you simply hate facts so you choose to ignore them - Which is too funny while at the same time sad -

The CrushKerry link is so stale - They did an elementary breakdown - A complete breakdown of the Newsweek poll has now been done by several sources -

And just for the record - my 5pt to 7pt Gallup findings....Shows I was Right...and you were of course Wrong.

You've been proven a fool - Gallup numbers out - And they are EXACTLY where I said they would be - Between 5 and 7pts -....NOT 11pts - (too funny) -

Huh? You love to change the debate when it's convenient for you, don't you? A prediction of poll outcomes was never a part of my argument, remember? What planet are you on anyway? Whether you succeeded in over or under predicting isn't saying much anyway since it's 50-50 either way. Besides, I'm sure another poll will come out in a couple of days with slightly different numbers. MY point, however, was that calling different numbers of Reps and Dems is not necessarily an over or under sampled methodology. But why am I repeating this for the 1'000th time? Oh yea, because you keep ignoring what you don't want to hear.

And just for the record - my 5pt to 7pt Gallup findings....Shows I was Right...and you were of course Wrong.

This is laughable. You're starting to make this sound like a seventh grade ego contest. In previous posts you claim you are not predicting, just guessing. I tell you repeatedly that I don't care what the numbers ultimately show, only that we didn't have enough information earlier to make predictions. But posts like yours reflect a deep insecurity that demands that every debate, every word be placed in a context of "I'm right, you're wrong", even when it's contextually nonsensical.

But all that is small potatoes. What's really disturbing is the fact that a deeper point, which I explicitly gave to you, is apparently over your head. You go to immense effort and work to try to convince everyone who reads at FR that GWBs campaign is not going as well as some might think. You go into great detail in trying to show lower poll numbers than what some may think will come out. But this is a public forum and your attempts to do that merely serve to push poll Bush DOWN! Yes, I know, everything you don't agree with you think is 'funny' and 'stupid' (brilliant retorts, by the by). But don't think this forum isn't public and that a lot people don't read your junk. This is the point you keep ignoring because it interferes with your bloated ego. If you truly support Bush, who's the fool, here?

As for the normalization, apparently you were too innumerate to know what normalization is because you never claimed that Newsweek used it. So, now you argue that they DO use it through 'voter turnout models', now that it is convenient to point that out. Perhaps you didn't realize that a 'model' is just another form of normalization? But earlier you argued that NO normalization is valid in polling, saying that it was 'obviously' weighted incorrectly because more calls were made to Republicans than Democrats. Okay, John Kerry. So, as far as what we were actually debating (as opposed to your phantom debate) it is YOU that is wrong, not me. But keep changing the debate as you like and I'll keep steering it back.

As for the normalization, apparently you were too innumerate to know what normalization is because you never claimed that Newsweek used it. So, now you argue that they DO use it through 'voter turnout models', now that it is convenient to point that out. Perhaps you didn't realize that a 'model' is just another form of normalization? But earlier you argued that NO normalization is valid in polling, saying that it was 'obviously' weighted incorrectly because more calls were made to Republicans than Democrats. Okay, John Kerry. So, as far as what we were actually debating (as opposed to your phantom debate) it is YOU that is wrong, not me. But keep changing the debate as you like and I'll keep steering it back.

This is too great! (and by the way...have you made another recent phone calls.....that just kills me - still too funny) -

And again, I said from the very beginning that NewsWeek used an incorrect weighted model (there has never been one post where I did not say this) - It is you that is horribly confused -

The very fact that you try and use that term....shows it doesn't apply - There was nothing "normal" about their weighted model - It DID OVER-SAMPLE REP's and UNDER-Sample Dem's -

GET a clue -

As I said, if you looked at NewsWeeks own internals and adjusted them for a more "normal" (correct) turnout model....it showd GWB would be up by 5 to 7pts....AND LOW AND BEHOLD.....I was right.....Gallup came out and showed GWB up by 7pts - <> Yeah, it was just a lucky guess and you are still right....Newsweek is such an accurate polling place -

You are simply ridiculously wrong about the Newsweek poll - Within 10 mins of looking at the internals......a freshmen in highschool statistics class would come to the conclusion that the weighting model was WRONG -

Yet you keep insisting that it wasn't - Bud, go look at the history of Newsweek polls - They are JUNK -

The fact that you cannot admit it was CLEAR that NewsWeek used an incorrect model proves this - 99% of the people here on the Freep.....know this to be true.....Yet you keep insisting that there was nothing wrong with NewsWeek having such a distorted weighted Model (because they were just "normalization") -

Polls legitimately use normalization; the crux of my argument, and that is a verifiable public fact. Something you denied, then later admitted (by admitting that models were used) without realizing it because you didn't know what normalization is. You were wrong. Then you tried to back-pedal. Deal. Repeating the same red herrings and phantom arguments doesn't make you right. It's also a clever but failed tactic to straw man me into saying that I supported or 'believed' in Newsweak polling. Never said that. Deal.

The very fact that you try and use that term....shows it doesn't apply - There was nothing "normal" about their weighted model - It DID OVER-SAMPLE REP's and UNDER-Sample Dem's -

Obviously you've never taken a statistics class, or you flunked it. Normalization has nothing to do with being "normal" (now THAT was laughable). Normalization is any mathematical formula that when applied to data results in output that is normally distributed against a dependent and independent variable. Genius.

Polls legitimately use normalization; the crux of my argument, and that is a verifiable public fact. Something you denied, then later admitted (by admitting that models were used) without realizing it because you didn't know what normalization is. You were wrong. Then you tried to back-pedal. Deal. Repeating the same red herrings and phantom arguments doesn't make you right. It's also a clever but failed tactic to straw man me into saying that I supported or 'believed' in Newsweak polling. Never said that. Deal.

It is YOU that is compactly wrong and doesn't know what a weighted model is -

I said in my FIRST post on this thread that Newsweek used an incorrect weighted model - Get that??? -

Yet, in your own words above - you suggest I didn't say this.....Where are you from?? -

In my first post (and in about every post after that) I have said Newsweek used an incorrect weighted model?? -

How can you suggest I didn't say that....then switched and said they did?? -

You are nuts - and you have been made a fool by your continued insistence that Newsweek is a reliable polling place - It is not!! - And anyone in the bizz knows this -

Obviously you've never taken a statistics class, or you flunked it. Normalization has nothing to do with being "normal" (now THAT was laughable).

That was a joke on my part - The "normal" comment - But obviously you didn't get it - (and to think I almost took that out...knowing it would go over your head) -

Again, understand that Newsweek polls are junk - they used an incorrect weighted model - Period! -

Facts mean things - and Newsweek used an incorrect model - This is clear -

AbleChair - Get over it - You have been proven to be fool - that you fell hook-line-and-sinker for a biased / junk Newsweek poll -

You wanted the 11pt lead to be true...and you could care-less about facts -

Others on here are willing to face facts and admit that while GWB doesn't have a 11pt lead.....by looking at the internals of the Newsweek poll....we could come to a relatively honest assumption that the GWB lead was more around 5 to 7pts -

Of course you disagreed with this....only to within 5 hours or so be proven wrong - (Gallup came out and agreed that GWB was up by around 5 to 7pts) -

You have to face reality -

Wow, lots of red herrings. Congratulations, you've won about 5 arguments in that post with yourself. I never argued any of that. Read carefully. I stated that typically polls use normalization to get correct results and that you can't assume that because the number of Reps and Dems called is different, that that alone means that they are weighted wrong. They can only be weighted wrong if the normalization is invalid; i.e. the 'models' you finally conceded existed are wrong. You did NOT claim that at first, only that the weighting was 'incorrect'. That tells us nothing about whether or not you believe normalization, or models, were used. Furthermore, if you concede models were used AND that the weighting is incorrect then it is then incumbent upon you to prove why the model is invalid. You never did this. You just pretty much ignored the discussion of normalization. An incorrect weighting could occur if, say, they were simply too lazy to get the numbers right and they never used models at all. Why is that so complicated for you to understand? Now, honestly, do you really know what normalization is? Do you understand that there are many kinds of normalization, some of which may have nothing to do with voter turnout? I'm really curious as to your educational background at this point. So, I'm from Earth, where are you from? Fool, Stupid, Nuts? Gee, I thought there was a policy here about name-calling? I guess that means I have a green light to unleash the same on you?

They can only be weighted wrong if the normalization is invalid; i.e. the 'models' you finally conceded existed are wrong. You did NOT claim that at first, only that the weighting was 'incorrect'. That tells us nothing about whether or not you believe normalization, or models, were used.

Game - set- and match!! - You lose - I have talked with others on here about Weightings (models) since I have been signed up here on the freep -

I made it clear at the start of this thread that Newsweek used an incorrect weightings / model - It is you that now realizes you have been made a fool.....and thus you are trying to adjust the argument to semantics (I said weightings and not model) -

When the correct answer is I used both weightings and turnout model -

And as I have stated - I have talked with dozens of other freeprs about Newsweeks turnout model and the weightings of their model being incorrect -

So again, Newsweek polls are junk - their weightings were WRONG from the start -

And it appears I was correct - Gallup came out to show that if a more reasonable weighting / model was applied GWB lead was around 5 to 7pts....(just as I suggested) -

You simply were proven wrong by trying to assert one could not make a reasonable assumption that the Newsweek poll was incorrect by looking at the internals -.....Yet I said one could make this assumption....

Ahh, now that's a little closer to reality. Except! It doesn't matter what you said to other Freepers, my friend, you were debating ME, not them. Do you really think I'm gonna go read all the junk you've posted over the last 4 years or so before I post a reply to you? Get real. As for the above comment, yes, I said you cannot assume a weighting is wrong simply because the numbers called are different. So, you're close, but not quite there. And it is STILL true that you cannot make that assumption unless you also debunk the normalization technique, which you did NOT do; not in your posts to ME.

You know, I once ran into a poster on FR that just couldn't stand the fact that he was wrong, and that I proved him wrong. He did the same thing you're doing. He started by throwing invectives, just like you. But then he threatened to "kick my a$%". His account was deleted, but needless to say, I'm wondering when you're gonna reach that point of frustration and do the same. Posters like you just can't deal with being disproven. Take a deep breath and just admit you were wrong when you said that if the number of Reps and Dems called is different, then the poll MUST be wrong.

Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.