I HAVE JUST UPDATED THE EXIT POLL ANALYSIS: THE RESULTS ARE ASTOUNDING.

[TruthIsAll]

Today I updated the analysis to include the absolute, final
vote totals as requested by another DUer. I had used the
preliminary results as of Nov 3, disregarding any changes to
the actual reported totals. The final numbers make the results
even more improbable, if that is possible.

I do request any enterprising DUer to check my numbers. If you
do, note that the vote and exit poll percentages have been
converted to their 2-party equivalents and add to 100%. If
there are errors in the updated voting percentages, please let
me know.

Now, here is the crux of the update.
In the original analysis, 
1) 16 states deviated beyond the MOE to Bush.
The latest numbers now show that TWENTY (20) did. 
The probabilities of this occurrence have gone beyond the
known universe. So unlikely, that Excel cannot compute it.

2) 41 states deviated to Bush, regardless of MOE. 
The latest numbers now show that FORTY-THREE (43) did. 
This reduces the probablity to one in 2.9 Million. 

I will check the numbers again. I believe they are accurate.

Kerry's exit poll and vote percentages are based on the
exit poll numbers downloaded by Simon at 12:22 AM Nov 3. 

The numbers have been converted to two-party percentages
so as to total 100%. The purpose was to maintain
comparability to other pre-election projection models. The
adjustments are proportional to the exit poll and vote
percentages. The post-adjusted numbers are in proportion to
the original numbers. There is NO BIAS for Kerry or Bush.

For example: 
Assume Bush won the state vote 50%-49% with 1% going to third
parties. 
Bush's adjusted two-party percentage is 50/99 = 50.505%
Kerry's two-party percentage is 49/99 = 49.495%

These are the relevant statistics from the table:
N = exit poll sample size
Poll = Kerry's exit poll percentage
Vote = Kerry's vote percentage
Diff = Kerry deviation from exit poll to vote

MOE = Margin of error = 1/sqrt(N)
StDev = standard deviation = MOE /1.96 (95% confidence level)

Prob = Probability of vote deviation based on Diff and StDev
Prob is calculated for each state using the Excel Function:
Prob = 1-Normdist(Poll, Vote, StdDev, true)
Odds = odds of occurrence = 1 in (1/Prob)

Analysis Summary
----------------
Bush vote tallies exceeded the exit poll MOE in 20 states.
The probability of this occurence is given by the Excel
formula:
Prob = 1- BINOMDIST(19,51,.025,TRUE)

The ORIGINAL odds of this occurring due to chance for SIXTEEN
(16) states was 1 in 13.5 trillion. 

In the NEW analysis, for Bush's vote tallies to exceed the MOE
in TWENTY (20)states, it is BEYOND the CAPACITY of Excel to
display the result - because the probability is smaller than
30 ZEROS to the RIGHT of the decimal point. And Excel only
displays the result up to thirty decimals. It is therfore
effectively zero.

****** The probability is VIRTUALLY ABSOLUTE ZERO *********

I cannot calculate the odds, because you can't divide by
zero..

As previously mentioned, the final voting numbers show that
exit poll deviations without regard to the margin of error
favored Bush in 43 states.

The probability of this occurence is given by the Excel
formula:
Prob = 1- BINOMDIST(42,51,0.5,TRUE)

The odds of this occurring due to chance alone: 
 **************  1 in 2.9 MILLION  *********************

Other stats:
The unweighted average Kerry deviation from the exit polls:
2.24%.
The unweighted average MOE for all states: 2.85%.

The MOE was significantly lower than the average (2.85%) in
the
battleground states where the sample size was large.

A total of 73,607 were polled nationwide.					

St	N	Poll	Vote	Diff	StDev	MoE	Prob  	 1 in	>MoE?	Favor
AK	910	40.5%	35.6%	-4.9%	1.7%	3.3%	0.002	524	yes	Bush
AL	730	41.0%	36.9%	-4.1%	1.9%	3.7%	0.014	70	yes	Bush
AR	1,402	46.6%	44.6%	-2.0%	1.4%	2.7%	0.066	15		Bush
AZ	1,859	47.0%	44.4%	-2.6%	1.2%	2.3%	0.014	72	yes	Bush
CA	1,919	54.0%	54.4%	0.4%	1.2%	2.3%	0.645	2		Kerry

CO	2,515	49.1%	47.1%	-2.0%	1.0%	2.0%	0.024	42	yes	Bush
CT	872	58.5%	54.3%	-4.2%	1.7%	3.4%	0.008	130	yes	Bush
DC	795	91.0%	89.4%	-1.6%	1.8%	3.5%	0.193	5		Bush
DE	770	58.5%	53.4%	-5.1%	1.8%	3.6%	0.003	385	yes	Bush
FL	2,846	50.5%	47.1%	-3.4%	1.0%	1.9%	0.000	4,799	yes	Bush

GA	1,536	43.0%	41.4%	-1.6%	1.3%	2.6%	0.112	9		Bush
HI	499	53.3%	54.0%	0.7%	2.3%	4.5%	0.622	2		Kerry
IA	2,502	50.6%	49.3%	-1.4%	1.0%	2.0%	0.091	11		Bush
ID	559	33.5%	30.3%	-3.2%	2.2%	4.2%	0.067	15		Bush
IL	1,392	57.0%	54.8%	-2.2%	1.4%	2.7%	0.056	18		Bush

IN	926	41.0%	39.3%	-1.7%	1.7%	3.3%	0.150	7		Bush
KS	654	35.0%	36.6%	1.6%	2.0%	3.9%	0.792	1		Kerry
KY	1,034	41.0%	39.7%	-1.3%	1.6%	3.1%	0.204	5		Bush
LA	1,669	44.5%	42.3%	-2.2%	1.2%	2.4%	0.040	25		Bush
MA	889	66.0%	62.1%	-3.9%	1.7%	3.4%	0.011	90	yes	Bush

MD	1,000	57.0%	56.0%	-1.0%	1.6%	3.2%	0.262	4		Bush
ME	1,968	54.7%	53.6%	-1.2%	1.2%	2.3%	0.154	6		Bush
MI	2,452	52.5%	51.2%	-1.3%	1.0%	2.0%	0.112	9		Bush
MN	2,178	54.5%	51.2%	-3.3%	1.1%	2.1%	0.001	797	yes	Bush
MO	2,158	47.5%	46.1%	-1.4%	1.1%	2.2%	0.101	10		Bush

MS	798	43.3%	40.2%	-3.0%	1.8%	3.5%	0.046	22		Bush
MT	640	39.8%	38.6%	-1.2%	2.0%	4.0%	0.277	4		Bush
NC	2,167	48.0%	43.6%	-4.4%	1.1%	2.1%	0.000	35,233	yes	Bush
ND	649	34.0%	35.5%	1.5%	2.0%	3.9%	0.773	1		Kerry
NE	785	36.8%	32.7%	-4.0%	1.8%	3.6%	0.013	75	yes	Bush

NH	1,849	55.4%	50.4%	-5.0%	1.2%	2.3%	0.000	94,466	yes	Bush
NJ	1,520	55.0%	52.9%	-2.1%	1.3%	2.6%	0.059	17		Bush
NM	1,951	51.3%	49.0%	-2.3%	1.2%	2.3%	0.026	39		Bush
NV	2,116	49.4%	48.1%	-1.3%	1.1%	2.2%	0.128	8		Bush
NY	1,452	63.0%	58.4%	-4.6%	1.3%	2.6%	0.000	3,468	yes	Bush

OH	1,963	52.1%	48.7%	-3.4%	1.2%	2.3%	0.002	624	yes	Bush
OK	1,539	35.0%	34.4%	-0.6%	1.3%	2.5%	0.330	3		Bush
OR	1,064	51.2%	51.6%	0.4%	1.6%	3.1%	0.601	2		Kerry
PA	1,930	54.3%	51.0%	-3.4%	1.2%	2.3%	0.002	566	yes	Bush
RI	809	64.0%	59.6%	-4.4%	1.8%	3.5%	0.007	147	yes	Bush

SC	1,735	46.0%	41.0%	-5.0%	1.2%	2.4%	0.000	52,161	yes	Bush
SD	1,495	37.8%	38.4%	0.7%	1.3%	2.6%	0.697	1		Kerry
TN	1,774	41.5%	42.5%	1.0%	1.2%	2.4%	0.801	1		Kerry
TX	1,671	37.0%	38.2%	1.2%	1.2%	2.4%	0.837	1		Kerry
UT	798	30.5%	26.0%	-4.5%	1.8%	3.5%	0.007	149	yes	Bush

VA	1,431	48.0%	45.6%	-2.4%	1.3%	2.6%	0.038	26		Bush
VT	685	65.0%	59.2%	-5.8%	1.9%	3.8%	0.002	666	yes	Bush
WA	2,123	54.9%	52.9%	-2.1%	1.1%	2.2%	0.030	34		Bush
WI	2,223	52.5%	49.8%	-2.7%	1.1%	2.1%	0.006	175	yes	Bush
WV	1,722	45.3%	43.2%	-2.1%	1.2%	2.4%	0.047	21		Bush
WY	684	30.9%	29.1%	-1.8%	2.0%	3.8%	0.182	5		Bush
	73,607									
Avg	1,443	48.82%	46.58%	-2.24%	1.46%	2.85%	0.1094	9		Bush
Med	1,495	49.10%	47.08%	-2.09%	1.32%	2.59%	0.0474	21		Bush
Min	499	30.50%	26.03%	-5.78%	0.96%	1.87%	0.0000	94,466		
Max	2,846	91.00%	89.43%	1.62%	2.28%	4.48%	0.8372	1		
								

[BlueEyedSon]

1. You are amazing, TIA

thx for all your efforts!

[berniew1]

5. Vote machine fraud, malfeasance & dirty tricks to reduce minority vote exp

explain the discrepiency between Exit Poll results and official votes

Florida, Ohio, New Mexico http://www.flcv.com/fraudpat.html
Texas(Austin,Houston,SanAntonio) http://www.flcv.com/texas.html
Pennsylvania http://www.flcv.com/mercerco.html
Washington http://www.flcv.com/snohomis.html
California http://www.flcv.com/orangets.html
New Mexico http://www.flcv.com/bernalil.html
North Carolina, Wisconsin, Indiana, Texas, etc.
(default straight ticket Dem to Bush)

[bleever]

50. I'm guessing that berniew1 will find the gun that's making the

smoke that TIA keeps pointing out.

"Default straight ticket Dem to Bush"????? How clumsy is that?

[TruthIsAll]

73. What one would have expected to see in the polls.

Bush "won" the popular vote by 3%, so you would expect the vast majority of state exit polls to reflect that and fall within the MOE. Twenty fell outside the MOE, where one would expect that only two or three at would at most.

This also applies to the National Poll, where the MOE was 1.0%. However you slice it, whether looking at the 20 state deviations outside the MOE (probability ZERO), or the fact that 43 out of 51 states veered to Bush (2.9 million to 1), or the fact that the Bush's National Exit Poll (48.22%) was 2.51% lower than his 50.73% final vote (2.3 million to 1).

[me b zola]

57. New & improved poll tax.

They never fooled me that they had changed their ways.

[TruthIsAll]

16. Note the following states which almost exceeded the MOE.

WV, WA, VA, LA, MS (check the deviations from the MOE - within 0.3%.

NM deviated by -2.25%, within a hair of the 2.26% MOE.

Bush almost had 26 states deviating beyond the MOE.

[TruthIsAll]

62. THE GRAPH: SORTED BY DEVIATION vs. MOE

Look at FL, PA, OH. All deviated by 3.4% to Bush, far beyond the MOE for each.

43 STATES DEVIATED TO BUSH, 30 BY MORE THAN 2.0%
8 STATES DEVIATED TO KERRY, THE MAXIMUM WAS 1.6%

[murray hill farm]

2. Thank you so much!

Clearly a lot of work there! Now what? We see that the election was a fraud..we know this...but what can we do? Must we just accept that our democracy is gone...and hope that our lives will go on without much change..must we just accept..and go on..and nothing changes?

[Fly by night]

56. No, YOU can speak out anywhere and everywhere.

The power of the information provided to us by TruthIsAll, Freeman, Berkeley Group, Phillips, etc. is in its persuasiveness to the average voter. When you can say to an average citizen that (according to Freeman's analysis of three states), you are twice as likely to win PowerBall with a single ticket as those deviations between the three states' exit polls and their "reported" votes occurred by chance, the citizen will understand that. And using TruthIsAll's earlier analysis of the deviations in sixteen states, that same voter can understand when you say they are 112,500 times more likely to win PowerBall on a single ticket then that those deviations occurred by chance, again they will understand that something is mighty fishy (and rotten) on the Potomac.

What we ALL have to do is to arm ourselves with the facts, think them through to present them in a fashion which is readily understandable and then find as many pulpits (literally and figuratively) to present the information from to the widest and most diverse audiences possible. We have been working hard in Tennessee to do that and the number of opportunities to present the 2004 election theft story continues to grow. That is one reason we are working to organize a national conference here -- to further expand the public awareness of what we know and to allow activists to congregate in order to improve our abilities to speak the same language in the most persuasive ways that we can.

By the way, I am very heartened that the 2004 election theft story is gaining traction. If we can increase the proportion of people who have questions and concerns about the conduct of the election by 50% in the past month (from 20% polled by Gallup in November to 30% polled by Annenberg in December) -- in the presence of MSM silence and/or derision about this issue, we are well on our way to the tipping point. It is incumbent on all of us to hasten that tipping point by speaking out as often, as clearly and as forcefully as we can. The electionfraud2004.org slideshow is a great start,and I've already supplemented it with about ten more slides I've made up that were gleamed from the analyses presented on DU (TIA's and others). (PM me if you want copies of those new slides.)

So that's what we do. We get busy educating our fellow citizens that their pockets have been picked. And there's no reason to wait on the MSM or any other entity to do this for us.

WE ARE THE ONES WE HAVE BEEN WAITING FOR.

[bleever]

3. Bring on the Knights of Nay.

Non-numerical synopsis: Bush did not get the most votes.

Something is absolutely fishy.

The exit polls, while they do not constitute legal proof of fraud, do prove that such evidence is out there, waiting to be found.

There is no plausible explanation for the unidirectional bias of the results. Not in the polling methodology, not in quirks of human preference, not in who supposedly votes earlier or later. None.

They'll be here soon, saying that this is not a smoking gun.

I'll grant them that. But the room is full of gun smoke.

It's only a matter of time.


TIA: :thumbsup:

[TwentyFive]

6. Yes - whoever proves election fraud deserves a holiday named after them

Just think - we could have a real modern day hero. Proving election fraud would be as great a feat as anything in US history. Our very democracy depends on truthful elections. Without it, we will become a dangerous evil empire.

[Peace Patriot]

68. "Proving" election fraud was never necessary...

...to correct and just political action in this matter. We have...

--an almost completely non-transparent election system
--a third of the country's vote with no paper trail, and even systems with a paper trail producing fishy and anomalous results
--Bush "Pioneers" owning the secret, proprietary source code that counts all our votes
--Bush "Pioneers" manufacturing and selling the states highly insecure, unreliable, hackable electronic voting machines and tabulators
--57,000 complaints to Congress of vote suppression in violation of the Voting Rights Act, and numerous machine malfunctions, errors and other anomalies, and all of this favoring one candidate and hurting the other, all across the land
--a mountain of inferential evidence that the outcome of the election was wrong

Conclusion: the election was INVALID on its face.

You don't have to prove Kerry won, or Bush lost. And you don't have to have "absolute proof" of election fraud. I repeat, the election was INVALID. It was characterized by extreme unfairness and highly suspicious election machinery and processes, as well as a highly suspicious result.

The problem is not--and has never been--finding a "smoking gun." The problem is POLITICAL: BushCons controlling Congress, the courts and the media, and the Democrats so disempowered (by both BushCon thuggery, and their own self-destructiveness) that they couldn't even insist on the simplest, most obvious elements of fairness in the election.

People, the problem is VERY SERIOUS. You could have a hundred "smoking guns" and it WOULDN'T MATTER.

We have suffered a fascist coup. Our democracy is hanging by the thinnest of threads. And personally I see only one last hope, and that is: a grass roots, state by state, county by county, effort to remove control of our election system from BushCon hands.

And if we can't get that done, it's all over.

[imenja]

4. you really are amazing

I'm in awe of this sort of statistical calculation. I'm literally mentally retarded when it comes to numbers, though I have strong verbal and analytical abilities. Hats off to you. I'm sorry I can't add anything useful.

[troubleinwinter]

7. I can only add: KICK!

[yurbud]

22. what does kick mean?

in this context? it sounds like an insider joke.

[troubleinwinter]

24. 'kick' is a post without content to move the thread up the forum page

so more folks will see it.

It is a courtesy to help others, so that important or interesting threads will not be lost.

Not an inside joke, a tool.

[gristy]

8. I'm afraid I have a suggestion that is more work - lots more...

What if the same analysis was applied to past presidential elections? Whatever the results, they could be very interesting.

[bardgal]

38. THAT IS BRILLIANT, & MAY JUST BE THE "PROOF" WE NEED.....

[Nothing Without Hope]

54. Yes, this is essential. I'm betting the skewed numbers...

...will be be statistically evident on a local level, for example in counties of Florida in 2000, but will not show up statistically in a national, state-by-state analysis. The 2004 election was fraud on a truly massive scale. Yes, it will be very interesting and must be done. I would bet there are people out there working on it now.

Even though this does not itself constitute a smoking gun, I agree that to anyone who opens their eyes it says that fraud did definitely happen. Perhaps it will motivate more people to search for the evidence that will stand in court, even with Repub judges. And then we are in new territory, I think. What kind of suit can be brought AFTER the vote certification and inauguration? Bush can claim he didn't know anything about it, so possibly not impeachable on its own.

[orpupilofnature57]

9. this has got to be worth a least a"Monica-gate", makes me choke on pretzel

logic, why isn't he constantly dogged?

[dzika]

10. Thank you for keeping on this topic

I finally feel like I'm starting to understand where these number are coming from.

[DELUSIONAL]

11. Kick

[rdmccur]

12. TIA, it is my

understanding that the exit poll data you are referring to has been weighted. Is that your understanding as well? I base my opinion on the data I saw posted by SCOOP (NZ).

[TruthIsAll]

14. Weighted data? I really have no idea. All I know is that these are the

numbers downloaded by Simon which caused the media to assume Kerry was the winner - until the data was "contaminated" after 1 am, enabling Ohio and Florida to go from Kerry to Bush.

[rdmccur]

32. Oops, At the top of the files

posted by SCOOP, which were purportedly from Mitofsky/Edison for the barious media, are the words. Here is from the 4 pm poll.

"Estimates not for on-air use
PRES04 - Vertical Percentages
Time Created: 11/2/2004 3:59:05 PM
Time of Weighting: 11/2/2004 3:59:05 PM
United States General Exit Poll"

[fooj]

13. You are the best!

It's people like you who make me believe that this world isn't going straight down the toilet...YOU ROCK!

[livvy]

15. The more I look at your data...

the more I'm beginning to understand the numbers. I'm not the brightest crayon in the statistics box, but looking at your numbers is providing a great learning process for me. Some of those states the numbers are just unreal (N & S Carolina, NH). I've always believed the election was fraudulent. I knew the moment I saw the "royal family" on TV election evening. Your work, I think, helps to clarify how it was done, especially considering the popular vote.
Keep up the great work, TIA!

[super simian]

17. "not the brightest crayon in the statistics box"

Hi :hi: from another dim statistics crayon with a nose for the "unreal." :hi:

[livvy]

19. Hi!

[Amaryllis]

18. TIA, does your brilliant work get passed on to Conyers or anyone who

will make use of it? I hope it isn't stopping at DU!

[Mistwell]

20. When will you deal with the HUGE GLARING HOLE?

There is a huge glaring hole in your assumptions. You know it. You've seen it. You responded to it once in a manner that was incredibly silly. It's time to deal with it TIA.

When you look at all prior US Presidential exit polls that are UNWEIGHTED, LIKE THIS ONE, you see the SAME OR GREATER DEVIATION FROM THE MARGIN OF ERROR IN FAVOR OF DEMOCRATS.

Give me the response. Tell me why this is not a basic, fundamental flaw in your assumptions. Your continuing lack of response to this, more than anything else, has convinced me that this data analysis you keep doing just proves the exit poll is exactly as accurate as it always was.

http://www.washingtonmonthly.com/archives/individual/2004_11/005178.php

[troubleinwinter]

27. Great. You stated that you are convinced the exit polls were accurate.

Your mind is made up.

No one here OWES you a response to anything, or to "give" you or "tell" you anything. If a "lack of response... has convinced" you, so be it.

[Mistwell]

31. He owes YOU a response

It's a flaw in his assumptions. YOU should want him to explain it.

I think there was fraud in the election. I am unsure if it was enough to tip the scale to Bush or not, but want to get to the bottom of it to know for sure. However, I think this exit poll stuff is a massive, distracting red herring. I want good people on this board to spend their energy going after actual fraud, rather than pretending this stuff is reliable or instructive or "evidence". All it does it give credibility to our opponants who call us wacky conspiracy theorists. It hurts the cause when otherwise logical people behave in an irrational manner out of emotion, ignoring all evidence to the contrary and exagerating weak evidence when ACTUAL STRONG EVIDENCE does exist and should be the focus of everyone's efforts.

[burned]

35. Mistwell

There are PLENTY of people putting time into other aspects of election fraud. However, you and a few other people spend an UNUSUAL amount of time (wasted) chasing TIA around to question his work.

You're wasting a lot of time that you could spend on something you consider worthwhile. You're not helping anyone by doing this.

It's sort of a joke.

[Mistwell]

40. Except there are not

Look at the threads up right now. Notice HOW MANY are exit poll stuff, and how few are actual fraud threads. The actual fraud is getting buried by TIA and others posting the same exact thing (sometimes with different wording) every day, multiple times a day.

It's worth it for a few of us to say "Hey, you guys, quit being distractic by shiney things and actually LOOK at what we are here for".

[burned]

43. Get out and post something shinier then!

and I'll go look at it too.

[troubleinwinter]

52. Why do you constantly post which kicks up these threads?

Go kick up the threads that you think are more important. Post there regarding fraud.

[Peace Patriot]

69. Mistwell: "It hurts the cause when otherwise logical people...

...behave in an irrational manner out of emotion, ignoring all evidence to the contrary and exagerating weak evidence when ACTUAL STRONG EVIDENCE does exist and should be the focus of everyone's efforts." --Mistwell

Have you read Dr. Steven Freeman, Dr. Ron Baiman, and Dr. Webb Mealy, on the exit poll discrepancies? Why are you picking on TruthIsAll? Why don't you write to these experts in top university positions whose work is constantly vetted and peer reviewed, and tell THEM they are behaving in "an irrational manner out of emotion, ignoring all evidence to the contrary...", when they write:

"This Excel workbook contains my independent and original analysis of 2004 presidential election results gathered from exit polls and from the New York Times tabulated results site. I have found what, on the face of it, appears to be dramatic evidence of election tampering." --Dr. Webb Mealy

"The conclusion (in his previous paper) that the discrepancy between the 2004 US presidential election exit poll predictions and the official count could not have been due to chance (UEPD:13) generated extensive public controversy when it was written, but now it is widely accepted. National Election Pool (NEP) pollsters have acknowledged that their polls deviate from official totals by 1.9% nationwide (a 3.8% shift from Kerry to Bush) and intimated that this deviation was caused by disproportionate numbers of Bush voters refusing to participate in the polls. Analysis of the available data and theory, however, strongly suggests that at least part of the discrepancy is due to miscount. Moreover, a review of 2004 election processes suggests little reason for confidence that the count reflects either the intent of the electorate or the way that the votes were cast." --Dr. Steven Freeman

"I conclude that, based on the best exit sample data currently available, neither the
national popular vote, or many of the certified state election results, are credible and
should not be regarded as a true reflection of the intent of national electorate, or of many
state voters, until a complete and thorough investigation ...is completed." --Dr. Ron Baiman

[flyarm]

34. ifffff............

if "you " know it , show it...no one "owes " you anything..do the work and then show it...or blow it!!:nuke:

i am a mental midget with this stuff ( checkbook needs accountant!..not me)

but if you are going to challange someones incredible work..like TIA ..then put it out there...don't expect anyone else to do it for you!!
thats just rude and uncalled for!!

thank you TIA for such diligent work .,.on behalf of the challanged math patrons!! you are remarkable!!

fly:hi:

[Mistwell]

41. I did put it out there

The link is in my post. It's out there. Go read it.

[MadisonProgressive]

58. You posted a link to a blog entry by someone named Kevin Drum.

1) Who the hell is he?
2) What are his qualifications?

[Mistwell]

64. http://www.tcf.org/

The data I posted is from the Century Foundation (Kevin and Washington Monthly - a worthy publication in its own right - was just the link to it. I find it rude to link directly to a PDF because PDF's can chew on people's computers if they do not expect it sometimes).

"The Century Foundation conducts public policy research and analyses of economic, social, and foreign policy issues, including inequality, retirement security, election reform, media studies, homeland security, and international affairs. The foundation produces books, reports, and other publications, convenes task forces and working groups, and operates eight informational Web sites. With offices in New York City and Washington, D.C., The Century Foundation is nonprofit and nonpartisan. It was founded in 1919 by Edward A. Filene."

They are generally fairly progressive. On the site you will find information about disenfranchisement of voters in this last election...so it's hard to claim they are biased AGAINST the fraud claim.

[Donailin]

60. The source of that link is not exactly

fair and balanced. you got any links by scholars that don't have "democrats suck" on their sidelines?

[Mistwell]

65. You have GOT to be kidding!

First, Kevin is NOT a repub!

Second, the source of the data was the progressive Century Foundation, not Kevin or the Washington Monthly. Century Foundation is leading the way AGAINST disenfranchisement of voters...hardly a "Democrats suck" source.

Seriously, did you guys even read the data? Are you saying that the data cited is faulty in some way? Because I was not citing any opinion, just the fact that the unadjusted exit polls from the prior US Presidential elections all showed deviation from the official results by more than the MOE. That's the entirety of the claim.

[euler]

87. When they say:

"but if you are going to challange someones incredible work..like TIA ..then put it out there", they mean that they want you to prove that TIA's math is incorrect, or, using the same exit poll numbers as TIA uses, come up with a anlysis that is better than TIA's.

They don't understand that no analysis of these numbers with the aim of proving or disproving fraud can be valid. It's not the math that's incorrect, it's the very idea that math can be used on these numbers that is incorrect.

You will NEVER win the hard core 'FRAUDISTAS' over - NEVER. It's in their blood. All you can hope to do, is whittle around the edges, and try to pull a few away from blind obedience to you-know-who.

[bardgal]

44. Interesting info on that link....however...

maybe it's just evidence they've gotten better at what they've been trying to do for years. I think it would be naive to believe that they're new to the fraud biz. Where we finally had hard evidence was the recount of the entire state of FL after 2000, when it proved Gore actucally won, and still the media misled the actual facts of that story, stating that Bush won, when Bush only won when only the counties Gore requested were recounted. But when the entire state was recounted, Gore won by a substantial margin. Switching over to predominately e-voting by 2004 made clean-up for the recount much easier if anything went not according to plan, as evidenced by Ohio this time.

[rdmccur]

51. See post 32 above

This exit poll data is evidently weighted not raw.

[Mistwell]

66. False

The exit poll data from the prior elections that I posted was NOT weighted. It SPECIFICALLY says that.

[rdmccur]

76. Agreed.

I was referring to the 2004 exit poll data.
Sorry for not indicating that more clearly.

[davidgmills]

82. You have not responded to me about your absurd assumption

I keep asking you why you assume that past election tabulations were right and past exit polling was wrong.

This is a pretty silly assumption.

You assume that the really difficult thing to do (count 100 million anything) is more accurate than statistical methods (far easier).

If there has been a skew to the Democrats in the past, as you say, why not assume that there has always been a Democratic undercount rather than an overpolling of Democrats? This is the logical assumption.

Maybe this year's skew was more pronounced than in the past, but if so, I think the assumption that should be drawn is that there was more Democratic undercount this year than in years past.

If you are so wedded to the idea that the count is correct and the exit polls are wrong, please do some analysis or research on the last census and find out just how accurately people think it was counted.

[yurbud]

21. Simple graph of your data (tells the story pretty well)

[Fly by night]

79. This is an impressive graphic. I would appreciate receiving a copy

I will PM you with my email address, and would appreciate your sending me the graphic in a format which allows it to be imported into a PowerPoint presentation or a MS Word document. This does such a good job of demonstrating the absurdity of the number and magnitude of deviations for Bush. Thanks for an impressive and understandable graphic.

[theresistance]

23. I note that where they favour Kerry

the difference is only small, but for Bush some of the differences are huge. Especially in Ohio and Florida.

[helderheid]

25. TIA you're wonderful and this MUST GET TO CONYERS and B.BOXER!!!!

Please please get this in the hands of the right people. Send it to Air America Radio and Democracynow as well!!!

[helderheid]

26. just nominated this.

[AtLiberty]

28. TruthIsAll --

Would you please provide a simple conclusion? Bottomline non-laymen terms, please.

I'm just can't study rows and rows of numbers. Sorry.

[New Earth]

29. i have the same problem

the only numbers i comprehend are 311 :shrug:

[TruthIsAll]

61. Ffocus on the fact that 43 out of 51 states (incl DC) deviated to Bush

from the exit polls to the vote tally. If Kerry deviated down, Bush deviated up. You would expect that they would each gain in about 25 states if it were a random event.

Its like getting 43 heads (or tails) in 51 flips of the coin. Try it yourself. The odds are 3 million to 1 against this occurrence.

Simliarly, one would not expect the deviations to exceed the margin of error (MOE) in 20 states.

The odds are 1 in 40 that the deviation would exceed the MOE in any ONE state. To exceed the MOE in 20 states is too high for Excel's normal distribution function to calculate.

[spooked911]

30. It simply shows that the exit polls for 20 states gave Kerry winning with

a veyr high likelihood, but rather Bush got more votes. Add up all these improbabilities and it is an astronomical number-- very unlikely that Bush won by chance. Meaning either there was fraud or the exit polls were not done properly.

[Laurab]

33. I'm no good at numbers, either - I wish I was

all I know is we got trouble - right here in the USA.

where's euler? Has he finally given up?

[helderheid]

36. I'm not either

but that graph made sense to me - thanks to whomever did that!!

[jkd]

45. Hello Helderheid

Fellow Utahan, I sent this communication to Dr. Freeman:

Dr. Freeman,
Why do you continue to cite the BYU exit polls as evidence of exit poll accuracy. Mifofsky projected Kerry at 30.5% and the students had Kerry at 26.5% in Utah. The Utah poll missed by .5% and the NEP was off by 4.5%. These data seem to contradict your suggestion that Mitofsky must also be accurate because they are professionals and not just students.

This was Mr. Freeman's response:


"Good point; I thought about your point when I wrote it, but it's next to impossible to reconcile every piece of data ... What do you conclude from this? Do you have a particular change that you suggest for the paper or it's conclusions?"

The Utah exit polls were far superior to Mitofsky because they were designed to predict the election unlike the NEP polls. They used 900 students to poll 90 precincts. Mitofsky only polled 15 precincts. The Utah polls were right on and NEP missed by 4.5%. TIA assumes all exit polls are created equal; they are not. If Mitofsky had properly conducted polls to predict election results, then all this analysis might mean something. What might this suggest about Mitofsky's polls in other states besides Utah.

I presented more information about the BYU polls to Dr. Freeman, but he has not chosen to answer my last reply.

[Peace Patriot]

70. jkd - post #45

"If Mitofsky had properly conducted polls to predict election results, then all this analysis might mean something." --jkd

1. As Dr. Freeman points out in his second paper on the exit polls, Mitofsky has stated without qualification that there is no reason his exit polls cannot be used to verify the election. So your point is moot.

2. Go back to original premises. The US was holding an election using widespread electronic voting for the first time, and a voting system that was highly controversial with many "red flags" for potential fraud: no paper trail, Bush "Pioneers" owning the secret, proprietary source code that counts all the votes, etc. This situation CRIED OUT for verification. Exit Polls are used worldwide to verify elections and check for fraud ESPECIALLY in this kind of situation. So...why DIDN'T Mitofsky, the networks, AP, the Democrats, SOMEBODY design an exit poll specifically to detect election fraud, instead of a demographic poll, which can be used to check election results but, curiously, provides a ready (and entirely phony) excuse for BushCons and BushCon media to deflect the impact of the exit poll result (a Kerry win)?

[jkd]

78. I don't think it's moot

I have no opinion why Mitofsky and the networks didn’t design a poll that could be used to verify an election.
Dr. Freeman apparently could not reconcile the differences between the BYU and NEP polls. They can’t both be right. I believe the Utah polls accurately predicted the election and the network polls didn’t. We just don’t have independent polls to collaborate the accuracy in the other states.
I believe the use of these polls to prove fraud in this election is suspect. I guess if you want to accept exit polls that are approaching + or – 5% MOE, then the Mitofsky polls could be used to call an election, but not a very close one.

[euler]

88. The expert here is...

....Mitofsky, not Freeman. And Freeman, who recognizes the pecking order, modified his paper. The December 29th version actually states the opposite.

The pollsters have taken great pains to argue that their polls
were not designed to verify election results, but rather to provide election coverage support to subscribers – as one set of data that the networks could use to project winners and to explain voting patterns, i.e., who voted for whom, and why people voted as they did.

As January 6th loomed, and the possibilty grew that he might have to testify, Freeman wisely decided to verify his information. In light of the fact that Mitofsky and Lenski have publicly stated more than once since the election that the exit poll numbers are not suited to election verification, Freeman made the wise move.

You ask:

"why DIDN'T Mitofsky, the networks, AP, the Democrats, SOMEBODY design an exit poll specifically to detect election fraud, instead of a demographic poll"

We live in a society based on capitalism. Customers order goods and services, and vendors fill those orders. MSM ordered a exit poll from Mitofsky and told him what they wanted from the exit poll. Mitofsky then designed the exit poll to their specifications. They did not ask for a exit poll that could be used to verify the election. Simple as that.

[zimba]

37. Whoa. Kinda hard to question, probably why the MSM decided

early on to ignore the data being posted on the web concerning exit poll discrepancies. But this makes it really obvious. REALLY OBVIOUS.

[understandinglife]

39. Nominated (n/t)

[Time for change]

42. I did a similar analysis several weeks ago

based on previously released data.

With regard to states outside of the margin of error I got almost exactly what you did in this analysis. I had 18 states outside of the MOE -- the same that you have, minus CO and UT. CO was barely inside the MOE. With Utah I rounded off the numbers because it wasn't a swing state.

[helderheid]

46. Please get in touch with Kathy Dopp

at http://uscountvotes.org/

She needs good statisticians.

[e-mail]

[The Time is Now]

47. Computational Question

I've been getting most of my news information from this site since before the election, but have only begun to post.

Could you answer a question about how the MOE is computed? There's something that I must be missing. I've never studied statistics, so any help would be appreciated.

You say,

N = exit poll sample size
MOE = Margin of error = 1/sqrt(N)

It would seem to me that a reasonable MOE would have to vary with BOTH the sample size AND the total number of voters.
So, let V be the number of voters who actually turned out to the polls for the given sample population. If N is nearly equal to V, then I would expect the MOE to be much smaller than if V is much larger than N. Simply put, I would trust the poll more, all else being equal, if 20% of the actual voters were polled, as opposed to 10%, as opposed to 5%. On the other hand, if
N = say, 1000, then the MOE is exactly the same whether it represents a voting population V of 1,000, 10,000, or 100,000.

What am I missing?

Thanks for your tireless work on all of our behalf. Keep up the great work.

[thanatonautos]

48. You're not missing anything ... sample size is assumed to be much smaller

than number of voters in all cases. This is called the
infinite population limit. It's pretty well
satisfied for the exit polls in question.

In the infinite population limit dependence of the margin
of error on the total number of voters vanishes.

This page has some information on the finite population
corrections, which you correctly note, do exist. You'll
have to search down the page, but it's there.

Estimating Parameters from Simple Random Samples

[The Time is Now]

53. Thanks

This helps a lot, and of course, now I'm more convinced. (like I needed to be more convinced - what's more convinced than 100%?)

[TruthIsAll]

59. MOE has nothing to with population size, just sample size.

The MOE for n= 1000 is a constant 3.1%, whether the polling universe is 1 million, 10 million or 100 million.

The MOE for a 10,000 sample is 1.0%, again regardless of how many are polled.

The formula is very simple:
MOE = 1/sqrt(N), where N= sample size.
There is no variable other then N.

The MOE is invariant of the population size, contrary to what many intuitively believe.

[thanatonautos]

67. True when population size is much larger than sample size.

This is just nitpicking, but anyway.

If n=1,000, and the polling universe is N=1,000,
then clearly the margin of error is zero, since
all entries in the list have been sampled.

The intuitive belief is actually therefore correct:
when the sample size approaches the size of the
polling universe.

Nevertheless, your approximation for the margin of
error is extremely accurate for the cases you list,
namely n=1000, or n=10,000, with N=10^6, N=10^7, N=10^8.

When n approaches a significant fraction of N, however,
there are finite population corrections to consider.

A conservative estimate of the standard error in
a sample percentage, sampling without replacement
from a list of zeros and ones, for a sample of size n
from a list of size N is that the standard error in
the sample is no greater than:

sigma = f * 50%/(n^1/2), with f = ((N - n)/(N - 1))^(1/2)

For your cases, we have:

(n=1000, N=10^6) f=0.99950037
(n=1000, N=10^7) f=0.99995005
(n=1000, N=10^8) f=0.999995

(n=10000, N=10^6) f=0.9949873
(n=10000, N=10^7) f=0.9994999
(n=10000, N=10^8) f=0.99995

So finite population size corrections to your estimate
of the mean sample error are not very large at all in
any of the cases you mention: the largest being 0.25% for
the case n=10000, N=10^6.

(These are only upper bounds, one can certainly do better
by using the sample itself to estimate the standard
deviation of the whole list.)

[Melissa G]

49. Kick for the amazing TIA! n/t

[GetTheRightVote]

55. Thank you TIA for all your help in putting the light of truth on election

:kick:

[intensitymedia]

63. Thanks for great work TIA - n/t

[Peace Patriot]

71. Fabulous work, TIA! KICK! n/t

[corbett]

72. Kick!

[Hugin]

74. Thanks TIA...

I am ever so grateful for your efforts.

[FogerRox]

75. Kerry won & We Can Prove it-damn TIA--u do rock

[bleever]

77. Kickin', on a Sunday afternoon.

[ClintCooper2003]

80. Isn't it kind of funny how when the shift favors Kerry, it's a small,

insignificant shift, but when it favors Bush, it's kind of a huge shift?

[Vektor]

81. Kick! Great work...

This is astounding....I hope it gets to the appropriate parties and is given the careful consideration that it deserves.

[seaclyr]

83. Two overlapping distributions?

I'm guessing there aren't sufficient numbers to really address this question, but is it possible that the data are consistent with two distributions, one centered around a roughly 3 percentage point difference from the exit polls, and the other centered around a zero point difference, each with a somewhat similar margin of error? If so, that might be consistent with a widespread "central" adjustment to the vote counts together with a smaller group of states that were left alone for a variety of reasons. I think one can easily come up with arguments why OR, CA, HI, TX, TN and the Dakotas should have been left alone, for instance.

[pixelthief]

84. kick n/t

[NationalEnquirer]

85. Simply amazing.

Once they release the actual numbers and they are leaked to the public, someone needs to produce the magnum opus of this statistical analysis, for dummies like me whose eyes glaze over a bit.

[GoSolar]

86. Thanks, TIA.

[hippiegranny]

89. even if I don't understand everything

you post... I think you are amazing!!!

Thank you, TIA.

[garybeck]

90. am I reading this right? about CA...

according to the chart, CA deviated in favor of Kerry? Why do people keep saying then that CA was rigged to trim off Kerry votes to help pad the popular vote to Bush?