Why all the exit poll statistics spewing around DU are crap

[timeforachange]

All the 250 million to 1 chance the exit polls are wrong are assuming a genuine random sample, which we know did not occur.

For whatever reason, women were over-sampled in the morning by large margins and this skewed the results.

Also, Drudge got 40 million hits on election day. Tens of millions of people saw the exit poll results at 1pm. We do not know what impact the early release of exit polls had on the election. They could have very well motivated republican types who thought about staying home to get their ass to the polls.

Either way, assuming the exit polls were completely random is wrong in light of these events.

[Tandalayo_Scheisskopf]

1. And you get your information from where?

n/t

[alittlelark]

2. uh, yeah.....

I'll bet you'll find some stat. people here who will debate this with you....I'll debate evolution if you want....

[Cobalt Violet]

3. How do you know women were over sampled?

[yorgatron]

6. that's just,what's the word i'm looking for? oh yeah

freep-tastic.

[alittlelark]

7. He read it in one of the RW websites.

[timeforachange]

8. do you people read the news?

http://www.washingtonpost.com/wp-dyn/articles/A41106-2004Nov10.html

Search google news for "exit polls oversampled women" and you'll get hundreds of other sources if the washington post doesn't meet your high standards.

[JohnOneillsMemory]

22. But you can also find most stories saying TWA800 wasn't shot down.

And it most certainly was. Hundreds of witness.
http://prorev.com/twa800.htm
Understand how controlled key stories are by CIA, management, etc.

Google Operation Mockingbird and Bill Casey's declaration that CIA controlled most prominent journalists just before his odd death.
http://www.whatreallyhappened.com/RANCHO/POLITICS/MOCK/mockingbird.html

[blue sky at night]

28. ok i have had enough.....

Screw you with your "you people"...oh ya the WP, they are the truth, ya right. The thing I dislike the most about the repubs is the outright racism, we are right and you are wrong attitudes. I spoke to an "aquaintance" of mine last night, (a repub) and he let out a long winded barage about how his son's friends moved into "the Hood" and how any white person would be.....Blah, Blah, Blah. I was disgusted. So Mr. Timeforachange, Go F... yourself!

[bsuz]

39. RE: I have had enough

Please expound.

[blue sky at night]

52. I know I may not have been clear.......

but what jumps off the page for me when I hear those words, "you people", just substitute any derogatory expletive: Nigg.., Jew, Liberal, etc. The right always prejudges. My "friend" spewed a bunch of Bigotry all in the name of keeping his son from being killed for venturing into "the Projects"....you know, a black neighborhood. This guy is obviously from the other side, and Racism/Bigotry is one of the things that I cannot tolerate.

[ailsagirl]

41. Oh, you mean the non-biased mainstream news??????????

We don't watch your news channel, Fox, that's for sure.

[Jazzgirl]

46. How long are you gonna last?

Take this shit somewhere else and peddle it!

[IdaBriggs]

4. Ah, but they were miraculously ONLY WRONG IN SWING STATES.

All those non-swing staters WEREN'T influence by Drudge or the woman thing.

Right. :eyes:

[zmdem]

5. Not to mention

is there a valid reason to suppose that those who vote early in the day are a neutral sample of the electorate as a whole ?

[WestHoustonDem]

9. Even without perfectly random sampling, the odds are

pretty slim for it to have played out the way it did. The exit polls are only being used as circumstantial evidence of problems. There are plenty of incidents that provide direct evidence of problems to back them up.

But if you want to accept that this administration and its supporters are above crossing the line to retain power, go ahead and believe. Personally, I didn't believe Clinton's denial he had sex with Lewinsky and I laughed hard when Nixon said he wasn't a crook. Maybe I'm just a cynic.

[jefferson_dem]

10. Crap? To prove that, you will have to offer better evidence than some

wild claim about oversampling women and trumpeting the number of hits on shit-face Sludge's scummy site. Try again maybe?

[RyomaSakamoto]

11. University of Pennsylvania: The Unexplained Exit Poll Discrepancy -Freeman

A BUZZFLASH NEWS ALERT

11/12/04 4:48 PM Update: PDF link goes to version "00l."

In "The Unexplained Exit Poll Discrepancy," Dr. Steven F. Freeman says:


"As much as we can say in social science that something is impossible, it is impossible that the discrepancies between predicted and actual vote counts in the three critical battleground states of the 2004 election could have been due to chance or random error."



The odds of those exit poll statistical anomalies occurring by chance are, according to Freeman, "250,000,000 to one." That's 250 MILLION to ONE.

He concludes the paper with this:


"Systematic fraud or mistabulation is a premature conclusion, but the election's unexplained exit poll discrepancies make it an unavoidable hypothesis, one that is the responsibility of the media, academia, polling agencies, and the public to investigate."


paper...
http://www.buzzflash.com/alerts/04/11/Unexplained_exit_poll_discrep_v00l.pdf

A BUZZFLASH NEWS ALERT
http://www.buzzflash.com/alerts/04/11/ale04090.html


Steven F Freeman (University of Pennsylvania) - Curriculum vitae ...
http://www.getcited.org/mbrz/11068805

[ailsagirl]

12. Another freep!! Geeez, they're like flies... SWAT

[jefferson_dem]

14. Yep. Amazing how simpleton-ish their arguments are too.

Total lamers.

[bsuz]

17. A Dylan Fan.... Finally!!!

Love it!

[email protected]

[jefferson_dem]

23. Oh geesh. Big time. None better. Over 4000 discs worth.

[bsuz]

26. Love BD!!

Just saw him Tuesday night in East Lansing. Go to see him 2-3 X a yr. What do you mean 4000?

[email protected]

[jefferson_dem]

31. Well...let's just say i'm a rather obsessed Dylan collector.

I have a field recording of nearly every single show he's ever played, over the past 43 years, including this one -- http://my.execpc.com/~billp61/110904s.html

I am happy to send you a care package. Drop me an email or PM if you like.

:bounce:

[bsuz]

42. Obsessed as well.

Write me at: ( as some people on this site are annoyed by this, and I really don't want to do that, they have a viable point, but they do have ten fingers, and ten toes, and any one them can choose another thread, right. Anyway, we'll leave it at that. Be in touch.-- Suz

[email protected]

[bsuz]

43. Trouble connecting

Do you have an E-mail address?

[bsuz]

47. Your address

I don't need to see the set list. I was there. Re-reading "Chronicles" tonight; only been waiting almost 2 1/2 yrs for that to come out. But I appreciate it nonetheless. Is your offer still valid?

[email protected]

[jdj]

24. yes they are back.

the admins shut down registration for a while, now it is open again, and they are back, I think.

[bsuz]

30. They are back.

Sorry, I will try to stay within the subject line.

[NightOwwl]

32. No need to be sorry bsuz...

everyone gets off topic once in awhile.

[bsuz]

35. Getting off Subject Line

I guess I was just a little "too formatted" in elementary school as far as "outlines" go. Appreciate your note.

[email protected]

[Zorra]

13. Katherine? Katherine Blackwell? Is that you? n/t

[bsuz]

15. Don't even come on this site without the facts.

You should apply for a job at ( you know where )

[proudbluestater]

21. Gee, did the LAST excuse get blown out of the water, too?

Remember the ORIGINAL lame excuse? "Democrats voted early." BS. The exit polls have *never* been WRONG, EVER, until the Bush Regime came into supposed power.

WaPo? NYTimes, they as bad as the rest of the media. Read an article earlier today on the TRADITION that mainstream media has had in protecting the Bush family.

I'll try to remember the link and post it later.

[NightOwwl]

Why do you start an inflammatory thread...

with absolutely nothing to back it up? I took the time to read some of your other posts...in one you refer to DUers as "you people" in a sarcastic tone.

What are you doing here anyway?

ETA: You did it again, as I was writing this post. Post #8.

How about you go hang out with "your people" instead.

[high density]

16. Tens of millions of people visiting Drudge?

I'll believe that when I see the logs with my own eyes. The people reading the exit polls were probably already motivated to vote no matter who they wanted to win. I do not buy the argument that exit polls on Drudge, Slate, or some other websites suppressed the turnout of Democrats and/or increased Republican turnout.

[jefferson_dem]

18. No shit. There's absolutely no evidence that publishing exit poll data

has any particular effect on voting behavior. None. And the last thing one would expect is that it would turn out more demoralized repukes.

These dolts are also the same ones who whined about the nets calling FL for Gore in 2000 before the polls closed, thus depressing Repuke turnout in the panhandle. Helloooooo...?!

[bsuz]

19. Drudge-Sludge

I don't think many people with any insight "tune in" to that site any longer. All I know is that the missives I've been reading on this site are clued in to that fact.

[bowens43]

20. Here we go again

another low post count poster doing all he can to discredit those seeking to ensure a fair and free election.

These guys are coming out of the woodwork.

[NightOwwl]

25. Gee, it's the same poster

who's pushing the Dems as Repug-lite strategy and Hillary for Pres in 2008. Why, it's almost like he/she wants us to lose.

:eyes:

[ogradda]

27. do you have a link showing

all the exit polls were done wrong?

[merh]

29. Please come back and post again when you obtain your PhD

from MIT and when you actually review and study all of the data and not some article from the washpost.
:boring:

[ailsagirl]

40. The thing about freepers is...

they thrive on annoying people.

They're also missing some screws.

And they like to bait us.

It's hard not to tell them to drop dead (I do it-- I know) but I wish a veil of nothingness would descend upon each freeper post so that he/she/it gets the dissatisfaction of NO REACTION from us. ;)

Just a thought...

[Sparkly]

33. The point is that they were not ALL wrong, they were selectively wrong

They were not uniformly wrong. They were wrong in certain states, and in certain counties in those states, and specifically in those areas where optical-scan ballots (hackable tabulators) were used. The variations for these areas being so out of whack compared with the accuracy of others is way beyond chance. That's what the statisticians are showing.

I'm not a statistician, so this is a non-expert's description, according to my non-expert understanding of the issue.

[Cat Atomic]

34. Hi, Karl!

[karlrschneider]

36. Hi! ....uh....oh....-that- Karl

never mind

:evilgrin:

[bsuz]

38. Yes, Hello Karl, Do you copy??

[peacetalksforall]

37. Your words match what right wing hosts and their expert guests are

saying.

[Swede]

44. I smell freeper.

Dude you just don't have enough posts to be dissing so many DUers.

[Awsi Dooger]

45. I agree the probabilities are exaggerated, but I dispute the reasoning

Drudge was completely irrelevant to the vote. The entire internet was irrelevant.

But exit polls are merely a sample, including a margin or error and subject to the same innacurate manipulation and evaluation as any sample. There are many instances of exit polls projecting the wrong winner, including the 1993 British general election when both preelection polls and exit polls favored labour, when the conservatives won by 7%, I think it was. Years ago I read an examination called, "A Nation of Liars?"

Here is a great link for anyone wanting to understand the exit poll process better, from the Mystery Pollster. Notice he posted this early on election day, refusing to allow early exit poll leaks on his site because he deemed the numbers possibly unreliable: http://www.mysterypollster.com/main/2004/11/exit_polls_what.html

"One or sometimes two interviewers will report to each sampled precinct. They will stand outside and attempt to randomly select roughly 100 voters during the day as they exit from voting. The interviewer will accomplish this task by counting voters as they leave the polling place and selecting every voter at a specific interval (every 10th or 20th voter, for example). The interval is chosen so that approximately 100 interviews will be spread evenly over the course of the day.

When a voter refuses to participate, the interviewer records their gender, race and approximate age. This data allow the exit pollsters to do statistical corrections for any bias in gender, race and age that might result from refusals. The interviewer will give respondents a 5 1/2 by 8 1/2 card to fill out that will include approximately 25 questions. Respondents fill out the survey privately then put the completed survey in a clearly marked "ballot box” so they know their identities cannot be tracked and their answers remain confidential.

Once the polls close, the interviewer will attempt to obtain actual turnout counts, and if possible, actual vote returns for their precinct. One of the unique aspects of the exit poll design is the way it gradually incorporates real turnout and vote data as it becomes available once the polls close. The exit poll designers have developed weighting schemes and algorithms to allow all sorts of comparisons to historical data that supports the networks as they decide whether to "call” a state for a particular candidate. When all of the votes have been counted, the exit poll is weighted by the vote to match the actual result.

So if this poll is so sophisticated, why can't we rely on the leaked mid-day "numbers” that will soon spread like wildfire across the web? 1) It is still just a survey – Even when complete, an exit poll still has the same random variation as any other survey. NEP says typical state exit polls will have a sampling error when complete of +/- 4% at a 95% confidence level, and +/- 3% for the national exit poll. Even if comparable to the final numbers – which they are decidedly not – the mid-day leaked numbers would have much greater error, perhaps +/- 7% or more. 2) The mid-day numbers do not reflect weighting by actual turnout – the end-of-day exit poll used to assist the networks in determining winners will be weighted by the actual turnout of voters at each selected precinct. The weighting will then be continuously updated to reflect turnout at comparable precincts. In the past, mid-day numbers have reflected a weighting based on past turnout, so the leaked mid-day numbers may tell us nothing about the impact of new registrants or the unique level of turnout this time."

On DU I am hardly married to the accuracy of this year's exit polls because I remember the mistakes in 2000 (Wisconsin, Iowa, Pennsylvania), and among the leaked numbers early in 2002 before VNS folded. I may have posted the only DU thread warning of the accuracy of early numbers, in the wee hours of election morning: http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=132x1267841

[seabeyond]

48. so the women were over polled just in the no paper reciept

areas and not the ones that have a paper trail.

repugs can come up with a better reason than that

[Moderator]

49. I'm locking this thread

Reason:

Flamebait

[Beetwasher]

50. LOL! For Whatever Reason!!!! That's Some Data Your Using There!

Dumbass...You are clueless about exit polls. The reason they are so accurate is because it's NOT random. It's interviews of people who JUST voted...They are the most accurate polls out there and always have been and still are. Man are you a moron.

[leesa]

51. Right. The old GOP talking point, "women were oversampled"

Before that one, it was "blacks were oversampled"

Your rationalizations are really pathetic! Go Away!