Stones-Cry-Out "What Went Wrong With The Exit Polling?

[bones_7672]

http://stones-cry-out.blogspot.com/2004/11/what-went-wrong-with-exit-polling.html

One key quote: "It’s in the method. Early voters vs. late…The assumption has always been that they had a handle on the differences between early and late voters. I have heard that they really did not think that there were many differences (in voting preference) at all. Apparently, Bush voters turned out later than Kerry voters. That surprised the pollsters from what I understand and that is what they are likely now assessing"

[Fovea]

1. Absolutely nothing.

There was nothing wrong with exit polling.
That is why it has been dicked with so much since 2000.

What was wrong was cheating, which shows up when you ask the voter.
Slava Ukraine!

[DenverDem]

2. Bull fucking shit.

All the people standing in line at the end of the day were Kerry voters.

[Quakerfriend]

5. Exit polls are very accurate

I spent many years doing clinical research at Penn, and though I am not a statistician, I know without a doubt that exit polls are very valid predictors of the outcome. This is not complicated, statistically. Anyone, with a cursory understanding of stats can tell you this. The larger the sampling size the greater the accuracy. And, we could not ask for a larger sample size than the millions of votes we count. The notion that ~1/2 of the population consistently voted earlier or later is utter nonsense. Exit polls are accurate. Why else would they withhold them?

[99Pancakes]

10. Ooo, Baby!

Way good point!! All those 7-8 hour Oppressed Ones hangin' in there til Shrubby's Hell froze over, chanting, "Hell no, we won't go!" (not going 'til I vote)
:crazy:

[Lizzie Borden]

3. Yeah, I gotta agreee with the 2 previous posters.

Slava (long live) Ukraine. They get it and aren't afraid to demonstrate for their votes. The police have gone over to their side. We COULD have done this. But we sat on our collective fat asses.

[BringEmOn]

4. Their candidate didn't turn tail and run

[Quakerfriend]

6. I think many are inspired by the rallies

in the Ukraine. I hope that a little kick from JK and we'll all be in the streets next week! Keep the spirit folks!!

[Clark2008]

15. As someone of Native American heritage

I think your picture there is hilarious!!!

Last week, my son went marching back into Kindergarten and informed the teacher that A.) Those weren't "Indians" that broke bread with the pilgrims at Thanksgiving. They were Native Americans. Indians are in India and B.) The country's first settlement was in Jamestown, Va. - not Plymouth Rock.

I'm guessing the teacher probably thinks I'm a knee-jerk reactionary, but I just hate my son learning misinformation!

:D

[kitp]

8. the difference is

that their candidate stated he believed the election was fraudulent and asked his supporters to take to the streets to protest...

...ours didn't.

Had Kerry said, on Nov 3, that we should take to the streets over the election, we would have, in HUGE numbers...

...he didn't...we didn't...

[99Pancakes]

11. I don't agree

I hold out that Kerry, being a thoughtful, intelligent man pouring meticulously over the data will speak out when he is good and ready.

[Branjor]

14. I hope he's good and ready soon. n/t

[stellanoir]

7. I've been foolishly musing upon

starting a party called the "united Serfs of america" of late.

Now I'm thinking it may be more appropriate to call it "Ukraine states of amerika."

Not an unintentional typo.

Hurrumphhhhhh.

[Quakerfriend]

9. Haaaaaaaaaaaaaa! LOL!

n/t

[peacetalksforall]

12. Removed dupe.

[peacetalksforall]

13. How To Rationalize A Lie Contest!

If they are pressed to provide an example to support their lie about the right wing voting later, they might come up with something like this: Right wing middle class voters only appeared at 5 or 6 in the afternoon because their employers would not allow them to leave during the day - they were going to meet friends for dinner or a game of squash after voting so they voted late. For those higher up on the ladder -their appointments were so important that they couldn't leave during the day and were lucky to leave by 5 or 6 since they usually work until 8.

Conversely, we must believe that people who voted Democrat only held night shift security or cleaning jobs - so they voted on their way home from work.

ANYONE who can fabricate a BETTER rational to substantiate the right wing lie about early and late voters deserves a guest spot on The Daily Show.

What examples would you give if you were a right wing liar?

Stupid. Once again they assume we'll swallow another lie. We are not the LIE SWALLOWERs.

[The Vorlon]

16. Exit polls, early vs late voters, etc...

This is only my second post on this board BTW.

So I have a few comments on the "accuracy" of exit poss and then a few general questions.

Firstly, exit polls are like any other polls, in the sense that they have margins of error - usually quite small, but still there.

For example, most of the exit polls collected about 2000 or so interviews per state. This equates to a error of a bit over 3% on the quoted "lead" that a candidate may have. We can thus expect that 19/20 polls will be within 3%, and about 2 out of 3 will be within 1.6% or so...

The big problem with the early exit polls was that they were not balance with regard to either gender or age.

The first batch of exit polls were about 59% female, versus 52% or so in the totality of the electorate. In addition, they had a much higher proportion of both younger and older voters (under 29, over 65) Both groups which favored Mr. Kerry over Mr. Bush.

If you take the totality of the final exit polls they were actually pretty darn close.

The basic principle of any polling is that you want your sample to look as much like the total population as possible, and the 2 pm sample (59% women, etc...) simply was not representative.

The second part of my post is a question:

I have heard that this forum is utterly intolerant of those who do not agree with them, and if somebody posts ideas and thoughts which do not match the collective wisdom of the forum, their posts are deleted and their registrations/user ids are canceled.

Is this true, or are you open to a broad range of ideas and perspectives?

Thanks!

[peacetalksforall]

17. Recommendation....

It appears that you hit the reply button when my message was on the screen.

I think you're contribution would fit better if you had clicked the reply button at the top of the page (before the list and tree of follow-up messages). I think you could still do that by copying and pasting to a new post that is a reply to the first message.

I think you can then go back and edit your reply to me by erasing and saying something like dupe. There may be a better way and someone will probably advise you.

IMO only, this list is quite open to opinions of members. Sometimes, a reply may sound caustic for a number of reasons. There is an intolerance of what is called freepers who sign up to deflect and ridicule subjects, statements, arguments. They are operatives. With so many people joining this forum, some people become impatient because over time they have advanced in their knowledge and when someone joins, they may not want to explain what might be considered old knowledge. There is never 100% consensus.

Your days will be lucky when the knowledgeable and the experienced step in to refute a fact because you will always be learning something from it. Supporting factual statements is important. If not a substantiated fact, it is a theory, belief, gut feeling, or premonition. When someone presents the latter as fact - sparks can fly. When people put two and two together in a way that others think is the wrong way - sparks can fly.

[buddysmellgood]

18. Male/female ratio is irrelevant

Explanations put forth by the Washington Post charge that samples may have included too many women, too few Westerners, not enough Republicans, etc …” Regarding the first part of this critique, Morris writes:
The very first thing a pollster does is weight or quota for gender. Once the female vote reaches 52 percent of the sample, one either refuses additional female respondents or weights down the ones one subsequently counted. This is, dear Watson, elementary.

Moreover, the issue of male/female ratio is irrelevant. CNN and others released data presenting male and female preferences separately, thus automatically weighting sex appropriately.
Other potential imbalances are part of normal sampling error. A random sample would result in the poll precision and confidence intervals that I reported. Under such conditions, Republicans, westerners, etc., are equally (un)likely to be over- or under-represented. Imprecise representation is incorporated within the margin of error. (That’s why we have the concept of probability densities, margin of error, etc…. If you could choose a perfectly representative sample, you could predict outcomes precisely.) In theory, techniques to ensure sample representativeness20 make the exit polls be even more accurate than my analysis indicated, thus making the observed discrepancies even more unlikely.

(This is taken from a paper by Steven Freeman of the University of Pennsylvania..

[newyawker99]

26. Hi The Vorlon!!

Welcome to DU!! :toast:

[buddysmellgood]

19. By this logic, Republican voted late, but only in 3 battleground states?

Kind of stretch.

[tandem5]

20. exactly... that assumption relies on all or most of the states

showing an incorrect Kerry skew.

[Straight Shooter]

21. Cherry picking the exit polls.

It either applies to all states, or to none of the states.

They're trying to make everyone focus on a few states, as if the other accurate exit polls never existed.

My response is always: Look at Oregon. People dropping off their ballots (which can also be mailed in), and exit polls of those voters matched almost to the percentage point the final tally.

Oregon is the benchmark.

[proudbluestater]

22. Bushshit!!

The exit polls have always been very reliable in that they check people who have ALREADY vote. Very small margin of error involved.

Up until 2000, they were always right on the money. Now we're told to believe Kerry voters voted early? Pure bullshit. No amount of spinning will make this NOT smell fishy.

[Patsy Stone]

23. Here is Nov 1 frozen in time

http://www.ariannaonline.com/forums/showthread.php?t=15 ...

I'm just going to clip a bit from one post:

"In 2002, multiple races were swung as the result of a "defective chip" found in DIEBOLD machines. In precincts in which the chip was replaced, the vote swung back to what pollsters had predicted. Only a handful of the known defective chips were replaced."

Also, in there somewhere is this Fox poll:
Look at these responses...to a Fox poll.
http://www.foxnews.com/projects/pdf/110104_poll.pdf

And you want to tell me nothing smells fishy?

[tandem5]

24. Ok let's entertain the idea that the methodology is to blame...

So we need other data conducted by another exit poll company. Thanks to the 2000 election all the media networks were too afraid to call the election on their own so they all used the one polling company. Different company, different methods, and, more importantly, different sampling. If that data were to show up the same then that casts serious doubts on methodology as the cause.

[seaclyr]

25. No, no, no.

All the evidence so far from vote tallies suggests that Bush was ahead (in fact way ahead, perhaps suspiciously so) in early vote counts. See Michael Keefer's article at http://globalresearch.ca/articles/KEE411A.html Because of this an early vs. late argument to account for the very unlikely possibility of exit polls being off seems to be dead in the water.:tinfoilhat: