THE PROBABILITY IS ZERO: THANK YOU, BILL GATES, FOR GIVING US EXCEL.

[TruthIsAll]

It makes it all so easy to raise the eyebrows of those who
refuse to believe.

Historically, exit polls have been much more accurate than
standard polls. In  prior calculations, I have
(conservatively) used the standard polling MOE methodology to
compute probabilities based on deviations from the Exit polls.
Using standard polling MOE's does not make much sense
intuitively. We should consider historically proven EXIT POLL
accuracy.

So let's be a little more realistic this time and assume that
the Exit Poll margin of error in each state is 2.0%, even
though all historical evidence indicates that it's less than
half that (see Germany, Ukraine, France etc.) So we are still
being very CONSERVATIVE in this assumption.

Now let's take another look at the election results:
For Bush, vote tallies in 23 states were outside the 2.0% MOE
- all in his favor.
For Kerry, vote tallies in 2 states were outside the 2.0% MOE
- all in his favor.

So here we go again. I'm almost sorry to do have to do this. 
Let's calculate the probability (for Bush) of this occurring
under the 2.0% MOE criteria.

I ran the numbers in Excel as before, with a single input
parameter changed to calculate the odds that at least 23
states would be beyond the the MOE. 

We input 22 as the number of states inclusive. The probability
is still .025 that the MOE would be exceeded. See the
description of the BINOMDIST below.

So, once again, let's calculate the probability:
 Probability=  P = 1-BINOMDIST(22, 51, 0.025, TRUE)

             P =  0.000000000000000000000000000000E+00

IT'S A BIG FAT ZERO.ZILCH.NADA! THIRTY OF THEM. 
EXCEL WON'T PRINT ANY MORE THAN 30 DECIMALS! 

To compute the odds, we must calculate 1/P.
But wait!
P = ZERO
We can't divide by ZERO. No can do. 
What does this mean? 

It's BEYOND INFINITESMAL!
It's IMPOSSIBLE!

THE DEVIATIONS IN FAVOR OF BUSH COULD NOT HAVE OCCURRED BY
CHANCE!

THE PROBABILITY THAT IT COULD HAVE BEEN DUE TO CHANCE IS ZERO!

THANK YOU, BILL GATES, FOR GIVING EXCEL TO AMERICA.

OH, AND THANK YOU, TOO, LOTUS. 
I USED 1-2-3 LONG BEFORE EXCEL. 

********************************************************************
Notes:
BINOMDIST(number_s,trials,probability_s,cumulative)

Number_s   is the number of successes in trials = 22 (at most
22 would fall within the MOE, at least 23 above)

Trials  is the number of independent trials = 51
Probability_s   is the probability of success on each trial=
.025.

If cumulative is TRUE (which it is), then BINOMDIST returns
the cumulative distribution function, which is the probability
that there are at most number_s successes; if FALSE, it
returns the probability mass function, which is the
probability that there are number_s successes.

*********************************************************************


Size refers to the exit poll sample size for the given state.
The percentages are Kerry's Exit Polls and reported Votes.

State	Size	Exit	Vote	Diff	StDev	MoE	Prob  	>MoE?	Favor
DE	770	58.50%	53.54%	-4.96%	1.80%	3.53%	0.29	yes	Bush
NH	1849	55.40%	50.51%	-4.89%	1.16%	2.28%	0.00	yes	Bush
VT	685	65.00%	60.20%	-4.80%	1.91%	3.74%	0.60	yes	Bush
SC	1735	46.00%	41.41%	-4.59%	1.20%	2.35%	0.01	yes	Bush
NE	785	36.76%	32.32%	-4.44%	1.78%	3.50%	0.64	yes	Bush

AK	910	40.50%	36.08%	-4.42%	1.66%	3.25%	0.38	yes	Bush
AL	730	41.00%	37.00%	-4.00%	1.85%	3.63%	1.53	yes	Bush
NC	2167	48.00%	44.00%	-4.00%	1.07%	2.11%	0.01	yes	Bush
NY	1452	63.00%	59.18%	-3.82%	1.31%	2.57%	0.18	yes	Bush
CT	872	58.50%	55.10%	-3.40%	1.69%	3.32%	2.24	yes	Bush

RI	809	64.00%	60.61%	-3.39%	1.76%	3.45%	2.68	yes	Bush
MA	889	66.00%	62.63%	-3.37%	1.68%	3.29%	2.21	yes	Bush
PA	1930	54.35%	51.00%	-3.35%	1.14%	2.23%	0.16	yes	Bush
MS	798	43.26%	40.00%	-3.26%	1.77%	3.47%	3.29	yes	Bush
OH	1963	52.10%	49.00%	-3.10%	1.13%	2.21%	0.30	yes	Bush

FL	2846	50.51%	47.47%	-3.03%	0.94%	1.84%	0.06	yes	Bush
MN	2178	54.50%	51.52%	-2.98%	1.07%	2.10%	0.27	yes	Bush
UT	798	30.50%	27.55%	-2.95%	1.77%	3.47%	4.78	yes	Bush
ID	559	33.50%	30.61%	-2.89%	2.11%	4.14%	8.60	yes	Bush
AZ	1859	47.00%	44.44%	-2.56%	1.16%	2.27%	1.38	yes	Bush

VA	1000	47.96%	45.45%	-2.50%	1.58%	3.10%	5.66	yes	Bush
LA	1669	44.50%	42.42%	-2.08%	1.22%	2.40%	4.49	yes	Bush
IL	1392	57.00%	55.00%	-2.00%	1.34%	2.63%	6.78	yes	Bush
WI	2223	52.50%	50.51%	-1.99%	1.06%	2.08%	3.00		Bush
WV	1722	45.25%	43.43%	-1.82%	1.20%	2.36%	6.54		Bush

NM	1951	51.30%	49.49%	-1.81%	1.13%	2.22%	5.54		Bush
CO	2515	49.10%	47.47%	-1.63%	1.00%	1.95%	5.15		Bush
IN	926	41.00%	39.39%	-1.61%	1.64%	3.22%	16.42		Bush
GA	1536	43.00%	41.41%	-1.59%	1.28%	2.50%	10.69		Bush
MO	2158	47.50%	46.00%	-1.50%	1.08%	2.11%	8.17		Bush

NJ	1520	55.00%	53.54%	-1.46%	1.28%	2.51%	12.67		Bush
WA	2123	54.95%	53.54%	-1.41%	1.09%	2.13%	9.70		Bush
IA	2502	50.65%	49.49%	-1.15%	1.00%	1.96%	12.41		Bush
AR	1402	46.60%	45.45%	-1.15%	1.34%	2.62%	19.55		Bush
KY	1034	41.00%	40.00%	-1.00%	1.55%	3.05%	26.01		Bush

OK	1539	35.00%	34.00%	-1.00%	1.27%	2.50%	21.63		Bush
MI	2452	52.50%	51.52%	-0.98%	1.01%	1.98%	16.47		Bush
NV	2116	49.35%	48.48%	-0.87%	1.09%	2.13%	21.29		Bush
ME	1968	54.75%	54.08%	-0.66%	1.13%	2.21%	27.80		Bush
MD	1000	57.00%	56.57%	-0.43%	1.58%	3.10%	39.18		Bush

DC	795	91.00%	90.91%	-0.09%	1.77%	3.48%	47.96		Bush
MT	640	39.76%	39.80%	0.04%	1.98%	3.87%	50.72		Kerry
OR	1064	51.20%	52.00%	0.80%	1.53%	3.00%	69.91		Kerry
HI	499	53.30%	54.55%	1.25%	2.24%	4.39%	71.10		Kerry
TX	1671	37.00%	38.38%	1.38%	1.22%	2.40%	87.10		Kerry

TN	1774	41.50%	43.00%	1.50%	1.19%	2.33%	89.68		Kerry
CA	1919	54.00%	55.56%	1.56%	1.14%	2.24%	91.35		Kerry
SD	1495	37.76%	39.39%	1.63%	1.29%	2.53%	89.65		Kerry
ND	649	34.00%	36.36%	2.36%	1.96%	3.85%	88.58	yes	Kerry
KS	654	35.00%	37.37%	2.37%	1.96%	3.83%	88.76	yes	Kerry

Avg	1450	49.18%	47.38%	-1.80%	1.42%	2.79%	21.67		Bush
Med	1507.5	49.23%	47.47%	-1.81%	1.29%	2.52%	6.66		Bush
				

[StephanieMarie]

1. As a fellow mathametician,

I love your posts!

[TruthIsAll]

31. HERE IS A GRAPH OF THE DATA

It looks like there were some Kerry shenanigans in ND and KS.

<sarcasm off>

[Scout1071]

67. Actually

I live in KS. In the burbs of KC. That variation is from liberals out here in the burbs and libs from Douglas County - ie The University of Kansas. It's located about 30 short miles from KC. Although still outnumbered by wealthy Bush supporters in my area.....I was inspired to see - quite unexpectedly - great support for Kerry in the burbs. Saw F 9/11 in two different burb theaters and both shows...sold out ending in standing ovation. And this is one of the reddest states of all.

It's those fuckers down in Southern Kansas and Western Kansas that vote Red.

[TruthIsAll]

89. OREGON HAD 100% PAPER BALLOTS; EXIT POLL WITHIN 0.80% OF THE VOTE

THAT, FRIENDS, SAYS IT ALL.
THE SIMPLE LESSON: NO BBV IF YOU WANT A FAIR ELECTION.
PEN AND PAPER IS CHEAP, CLEAN, SIMPLE, VERIFIABLE

YOU CAN'T CHEAT WHEN YOU HAVE A VERIFIABLE PAPER AUDIT TRAIL.

[TruthIsAll]

87. Thanks. It's appreciated.

BTW, if you have any suggestions and/or comments, please let me know.

tia

[TruthIsAll]

90. Then I won't stop...

...

[Occulus]

2. And for bonus points,

explain all that to people who have never used Excel :)

Not that I think you're wrong (I don't), I just want a clearer understand of the "what" of your post.

[mhr]

4. Simply Stated - It Is Mathematically Impossible For Bush To Have Won

Unless, fraud was in play.

Is that simple enough?

[Occulus]

6. Heh- yeah. I'd say that's enough.

I've never, ever once used Excel, so I'll just take your word for it.

[Chicago Democrat]

7. Yay! Can we prove that in court? Suspicions confirmed, now

what can we do about it.

[BrightKnight]

65. DNA and finger print evidence both depend on probabilities.

DNA and finger print evidence both depend on probabilities. They are both admissible in court. How is this any different?

Different states have different standards for matching points in a finger print. I know that DNA probabilities are calculated based on the matching points.

[unblock]

careful, now. it's statistically impossible for shrub to have won

unless there was some systemic difference between the exit polls and the official vote.

fraud is the obvious explanation, but in theory there are many, such as the entirely unsubstantiated banana republican claims that kerry voters were more likely to talk to exit pollers or that the kerry voters voted earlier, when the exit pollers were out in force.

but tia's statistical arguments put the burden of proof for these cockamamie hypotheses squarely on the banana republicans, who, as of yet, have produced a big fat zero.

[mhr]

16. Understand The Subtlety - The Probability That Systemic Problems

Occurred over all these states simultaneously must be low i.e. passive errors of the system.

The probability that fraud was in play to cause the simultaneous systemic problems must be much higher i.e. active errors of the system.

Maybe Truthisall has calculated these probabilities as well.

[TruthIsAll]

25. It's one thing to say it. It's another to show it in black and white.

Let those who would dispute these numbers try to spin them until they get blue in the face.

Come on, Conyers!
Come on, Dems!

We will NOT stand a repeat of the 2000 fiasco.

This one is for ALL the marbles.

[mdhunter]

35. That is not correct

What it says is that it is almost impossible for Bush to have exceeded the MOEs based on chance alone.

That's all the binomial distribution can tell us in this case. It can tell us nothing about what the cause of the deviance actually is, only that the cause is not chance alone.

Fraud surely is one possible explanation, and I think there was fraud. But there are dozens, hundreds if we want to get creative, of others.

Consider the following, the probability of being dealt any particular hand in poker is 1/2,598,860. So, if your sitting there looking at a 3C, 7D, 4D, 6H, and 9S you would have in your hand a combination of cards that, in theory would take 2,598,860 deals to get again, a very rare and unlikely event. But, that hand is utterly unremarkable. The point here is that, even if something is unlikely and of low probability the occurance of that event is not, a priori, important in any meaningful sense.

There are parallels with this voting issue. The probability of the final tally's devating beyond the MOE of last exit poll in each state is probabably 1/20, which expresses the industry standard 95% confidence interval. Since we're concerned with only Bush "victory" outside the MOE, the probability in each state is roughly 1/40. That means one time out of 40 the polling will be wrong, due to the chance error of the sample estimate. The power of statistics is very limited here, the poll may be wrong more often than that due to other issues, be they methodological, functional, circumstances beyond the scope of the study or false assumptions.

Granted, though we may not think it terribly noteworthy if the MOE was exceeded in one state, the aggregate of 22, or however many, states is a different thing. But it is not entirely dissimilar. True, the aggregate calculations will drive down the error due to chance to infintessimal levels, but it also sums the myriad other errors or effects that could account for the wrong numbers in the first place. The question statisticians must always ask is if the numbers they're looking at are actually meaningful.

I don't think this near zero number TruthforAll calculated is particularly meaningful. We could tell, on its face - without any statistical calculation, that it would be unlikely anyone could exceed the MOE solely due to chance in some many instances. After a certain point, a point we'd reach very early on, the magnitude of the number loses any significance in the real world. It does so partly because it so large, partly because it is express only that which we already knew, and partly because it cannot, and does not pretend to, account for any other possibilities of variation beyond chance. Those other possibilities are what are meaningful now, and we don't have them. What we need is an indicator of the liklihood of fraud compared to other sources or variation. What this near zero number does tell us, positively, is that it is more likely that fraud accounts for the difference than does chance, but how much more is anyone's guess. And, whether or not that is meaningful, I leave for others to decide.

[mhr]

46. In Practical Terms That The Layman Can Understand

It means that Fraud is most likely the overwhelming reason for the statistical anomalies.

[mdhunter]

51. I still don't know that to be true from these data

I can suspect it to be true based on other evidence, but no one could come to that conclusion based on these numbers.

And, I think it remains to be sseen whether or not fraud is the "overwhelming reason" for the differences in variance. We know that it's not chance and that it must be something else. We suspect fraud is a part of that something else, but we need tons more data, from many different sources, and different types of analyses before adjudicating the role fraud plays in this.

So far we only know that it plays some role, it still may turn out to be very small.

[TruthIsAll]

72. No, I must disagree with your final, bold statement.

You say:
"What this near zero number does tell us, positively, is that it is more likely that fraud accounts for the difference than does chance, but how much more is anyone's guess. And, whether or not that is meaningful, I leave for others to decide".

That is NOT what the analysis shows.

A ZERO probability means there is NO possibility WHATSOEVER that the deviations could have been due to CHANCE. NONE.

The deviations were due to something else:
1- Fraud
2- Lousy exit polling samples

But if it's lousy polling, one must still ask the question:
Why are 23 states of 41 exceeding the MOE in favor of Bush, but only 2 of 10 in favor of Kerry?

[TruthIsAll]

45. Disregard the Excel and math functions stuff.

Just know that 41 states shifting in Bush's favor, with 23 of them beyond the margin of error, is impossible.

[dargondogon]

47. It's impossible, but it happened

So how did it happen? That we can't prove.

[TruthIsAll]

73. We can't prove fraud, but independent investigators can. n/t

.

[Atman]

3. May I post this on my site?

http://www.notbannedyet.us

I'm doing some updates today. I think this would fit in nicely. I'd credit it to your DU screen name with a link back to here, or whatever you'd like.

[TruthIsAll]

8. Yes, of course. But wait 10 minutes.

Wait until I get the original polling numbers and post them as well.

[Atman]

12. It won't until a bit later today anyway

Thanks. I'll let the thread play out some more. Very nice job!

[TruthIsAll]

13. OK, IT NOW INCLUDES STATE EXIT POLLING AND VOTE

HAVE FUN.

[Chicago Democrat]

5. I love Excel, but you lost me...

Brain fart

[unblock]

9. rephrase, please: thank you LOTUS, for giving us 1-2-3

if you want to thank bill gates for stealing all of 1-2-3's features, be my guest. but please, give the real credit where credit it due.

honestly, bill gates never did anything more than figure out how HE could get rich from other people's inventions, innovations, and hard work.

and i'm not talking about this usual anti-capitalist argument about how owners get rich off their employee's. no, bill gates' way of getting rich involves getting rich off the work of OTHER COMPANIES, through stealing, undercutting, leveraging off their operating system monopoly, and other anticompetitive practices.

[Occulus]

10. I don't know that that relates to Window$, though....

The Commodore 64 had GEOS before there was a Mac, IIRC. And GEOS ran on a 64K machine. I mean, WOW.

It was primitive, but I believe it was also the first, or one of the first....

[TruthIsAll]

14. You are absolutely correct. I started using Lotus back in 1983.

I switched to Excel, reluctantly, in the nineties.

And here we are in 2004.

[Old and In the Way]

17. Truth Be Known........the 1st PC spreadsheet application was developed by

Dan Bricklin. It was called Visi-calc.

But I cut my teeth on 1-2-3. I'm so old, I remember having to boot the PC from MS-DOS from 5-1/4 floppy, then load 1-2-3 to run it....

[unblock]

19. true, 1-2-3 wasn't invented out of whole cloth either

but 1-2-3 actually WAS a creative innovation, and included many important features that visi-calc lacked (though i admit i haven't done this debate for so long i've forgotten the details. i know database functions were one large category that 1-2-3 added, and statistical functions as well, i think).

excel didn't really add ANYTHING that 1-2-3 lacked, unless you want to count integration with ms word and other ms office products, which is tantamount to admitting that they were leveraging off their other products.

[TruthIsAll]

20. Oh yes, I remember it well. But I never used it. My first: SUPERCALC

tia

[googly]

24. This will make you laugh.......

when I first started using computers on an IBM1620, to run a program,
first we had to run the "loader" deck of cards thru the card reader,
(we used only punched cards, no hard disk was available LOL), then we
loaded the compiled object language deck of cards, and then the
subroutine deck of cards, followed by input data deck.

The computer then could either type out the answers or punch cards.
Since the memory available to the programmer was so freakng small, most
of our engineering calculation programs required many segmentations to
do the entire job. Which meant the answers from first segment program
were punched out on cards, the next segment then processed (loader,
2nd segemnt program, subroutines, punched deck from 1st segment). One
of our programs required 25 segments to finish the job, so it took half
a day to make one run!

I was ecstatic when IBK came out with the 1130 which had a hard disk
so we did not need punched cards. If my memory is right, the disk
capacity was 400,000 bytes = 0.4 meg.

[TruthIsAll]

27. My first machine was a TRS-80. FOUR K of RAM. Tiny Basic. Tiny Chess.

I upgraded to a whopping 32K of RAM.
That was a powerhouse.

I chatted on The SOURCE Telecomputing network in 1978.

[spooky3]

29. Windows today is the Mac of yesterday.

[mulethree]

11. Thanks SUN for OpenOffice!

http://www.openoffice.org/

Open source, free, Office suite.

[TruthIsAll]

15. Any spreadsheet will do. Quattro Pro, Lotus, Excel...

I didn't mean to plug Bill Gates.

I just needed a catchy headline.

[Straight Shooter]

18. Here's a headline for ya

Screw you, Bill Gates, for giving us MS Access ;)

[unblock]

23. there ya go!

i'm so pissed that he bought out foxpro in order to deprecate it and replace it with ms access, which SUCKS.

in 9 months, i single-handedly created a foxpro call center application that handled simultaneous 150 users and 1/4 billion dollars worth of car loans, including sending out monthly statements with usps barcoding and discounts.

one of my programmers later ported the back end to oracle, in her spare time over the course of only 2 months.

ms access tends to choke on FOUR simultaneous users, and a visual basic/sql server application would have taken too long to develop.

[AntiFascist]

34. I agree....

and also Windows NT and its successors 2000 and XP. How many patches will be required before they are secure? Thanks for doing your part in destroying democracy.

[Helga Scow Stern]

21. I'll send to international monitors, in case they care.

[e-mail]
[e-mail]

[bleever]

22. A $5 calculator will tell you: *'s chances, 1 divided by 0, equals

ERROR.

Try it again.

ERROR.

One more time:

ERROR.

"Bush Re-elected"???

ERROR.

[Peace Patriot]

26. I'm wondering about...

...that little 2-state anomaly for Kerry. What do you make of it?

(I've been saying all error favors Bush, and people understand that as impossible--can't be innocent human or machine error. Now I can't say that--that every error or differential favors Bush. Boo-hoo. My sentences and paragraphs summarizing the election fraud will have to get longer.)

[DireStrike]

28. What if you subtracted 2 states from the * anomalies?

Would that be an acceptable practice?

I think it would be interesting to see a graph of the probabilities from the point where it becomes unlikely that it happened due to chance. IE, This bar is the probability of 2 deviations, this one is 3, 4, ... 23.

[WithStamina]

30. People won't buy this

There are plenty of explanations for this. Maybe certain voters were more likely to respond to the pollers. Maybe some people didn't tell the truth. Either way, Bush did win. All you conspericy therorists are making us look bad.

[noiretextatique]

32. capitulating to another stolen election

makes "us" look even worse. people will buy anything...ask the makers of the pet rock.

[Name removed]

33. Deleted message

Message removed by moderator. Click here to review the message board rules.

[pilgrimsoul]

36. Excellent analysis!!!

Please send this to Conyers, the Kerry campaign and others associated with the Ohio legal challenge, Olbermann, Palast, hell - anybody on the planet who can do anything with it. Many thanks for taking the time to compile this and share it with DU.

[Name removed]

42. Deleted message

Message removed by moderator. Click here to review the message board rules.

[WithStamina]

50. I don't support Bush

I just think that all the "proof" that's been offered up is a little flaky. Exit polls are by no means completely binding to how people actually voted. The possibility for fraud is there, but I've yet to see anything very convincing.

Again, I do not support Bush.

[bobbieinok]

59. exit polls are used to test validity of actual vote....every where but US?

[Faun Otter]

61. If there are plenty of explanations

Could you give us a few to consider?

Faun - who loved picking up dropped stacks of Fortran cards as a student

[badc0der]

86. pollsters underestimated growth in voter turnout in...

rural/suburban areas or over estimated turnout in urban areas.

[Kurovski]

66. "People won't buy this"?

Why? Does fuzzy math now hold a mandate?

And who is this "us" you speak of?

Welcome to DU, WithStamina! :-) From a conspiracy theorist!

(I sometimes forget to use the "Check Spelling" button, too!):-)

[TruthIsAll]

69. Plenty of explanations: Hackers. Spoiled ballots.Diebold. Es&S.

You say: "All you conspericy therorists are making us look bad". Really?

Your post made YOU look bad.

[rman]

79. all those "maybe's" and ignoring facts make you look bad

why would *especially in this election*
"certain voters be more likely to respond to the pollers"? (maybe)
"some people not tell the truth"? (maybe)

why would these things *especially in this election* add up to 23 outside the margin of error in favor of Bush and only 2 in favor of Kerry?

It can't happen by chance no matter how many maybe's you introduce. So what's your explanation?

[Zhade]

81. "Maybe certain voters were more likely to respond to the pollers."

Nice Republican talking point you've got there.

"Us". HAHAHAHA!

By the way, for the record: it's pollsters, not pollers.

[Name removed]

37. Deleted message

Message removed by moderator. Click here to review the message board rules.

[noiretextatique]

39. that's "an"

you are AN idiot :dunce:

[Atman]

40. Said the guy with the dope leaf avatar...

...who can't form a grammatically correct four-word sentence.

[understandinglife]

38. Forwarded/cross-posted as to spread the word....

....and, hopefully Rep Conyers will find ways to force Mr Mitofsky to release the 'raw' exit poll data by Wed. -- it must be scrutinized, immediately.

Thank you for another excellent post.

"Did Bush Know?"

[jkd]

43. Mitofsky still has some explaining to do.

I would like those early exit polls to be correct, but for my state, Utah, I don't believe they are.
Brigham Young University has been doing statewide exit polls for over twenty years. They have a very good reputation for accuracy. They show Kerry with 26.5% of the vote; Mitofsky's numbers are 4% higher. Exit polls are traditionally accurate; something is wrong.
If all states had independent exit polls, it might shed some light. Mitofsky must make his data and methodology public.

[Patsy Stone]

68. Here's the request from Dems for Mitofsky's Data (.pdf)

http://www.house.gov/judiciary_democrats/mitofskyelecinfoltr12304.pdf

[understandinglife]

70. Thank you and...

...I had read the letter within moments of it being released by Congressman Conyers.

But, as I thought about it during the past 24 hours I realized that Mr Mitofsky needed to be put on notice by the Congressman that a full list of pollsters, their contact information and details of exactly where and over what intervals each of them conducted interviews on 2 Nov 2004 was crucial information.

And, it is important for Mr Mitofsky to know now that we are all focused not just on the need for him to release the 'raw' data but also the exact information on whom collected that data at each polling station and at what time.

Peace.

"Did Bush Know?"

[Patsy Stone]

71. Here's hoping!

Between the data and Warren County, I may just go out of my mind with joy.

[mdhunter]

41. My calculations do not square with yours

Taking this new data, I approached the problem this way.

Treating the 25 cases where the MOE was exceeded by either candidate as the trials, we would expect Bush to win half, 12.5, if the variance was due to chance alone.

BINOMDIST(23, 25, .05, FALSE) which returns a value of .00000089407. Which is still monumentally unlikely, but less unlikely than yours.

I don't know which way is a better way of looking at this data. Great... thank's a lot, I'm going to have to spend the rest of my Saturday night thinking about this.

[TruthIsAll]

52. Your function gives a probability of 3.22759E-28

You better check it.

[dargondogon]

44. Put another way, there's a 100 percent chance of what?

OK, there's a zero percent chance Bush's collection of excessively large vote margins occurred by chance. That's not getting me excited. Tell me what there's a 100 percent chance of.

Is this it?

There's a 100 percent chance that vote tampering allowed President Bush to accumulate in 23 states unexpectedly high vote percentages compared with exit polls' predictions.

[TruthIsAll]

48. Almost. There is a 100% probability that the deviations in

Bush's tallies from the exit polls must have been due to either fraud or mistabulation or both.

It's like pornography. We know it when wee see it.

We can be damn sure it was FRAUD, and not just lousy exit polling.

Now they must prove the fraud with documented cases of machine "glitches" working in favor of Bush, minority disenfranchisement, voter intimidation, registration fraud, lack of polling equipment in democratic precincts, rigging of late night exit polls to match the rigged votes, etc.

[Faun Otter]

64. TIA - we can be sure it was not chance

I have noticed a frame set up by the hard right on this topic. They are asking us to "prove it was fraud." I say horse poop on that - we need reliable elections or the supposed winner (regardless of party) will be illegitimate.

I challenge the defenders of the current abomination of an electoral process to prove that it is reliable. Simple things like random audits and transparency would be a good start. Anyone opposed to such simple safe guards must have nefraious objectives. If anyone wants to argue with that statement, I challenge them to prove that people who do not want security measures on our voting system are not doing so in order to cheat in the next election.

You think there was no fraud? Prove it.

Faun

[TruthIsAll]

75. Of course it's NOT chance, I just wanted to show it mathematically.

The probability is ZERO if we assume a 2% Exit Poll MOE for each state (that's conservative).

The odds are 1 in 13.5 TRILLION if we use the standard (pre-election) state polling MOE's based on sample size. This is too conservative because we are dealing with exit polls, not standard polls.

[Quakerfriend]

54. Stats are quite accurate

I, for one, can't believe more academic-types aren't screaming from the roof tops!

[SoCalDem]

58. 110K x 31 states = 3.41 million mandate

:(

[jfern]

49. MOE varies with sample size

The standard deviation goes as Sqrt(p(1-p)/N)
MOE is roughly twice thise.
There's no way HI has only a 2% MOE.

Here's my check:

Outside of MOE:
DE, NH, VT, SC, NE, AK, AL, NC, NY, CT, RI, MA, PA, OH, FL, MN, AZ, LA

Inside of MOE:
MS, UT, ID, VA

That's 18 out of the MOE

It's still about 1 in 2 Quadrillion= 2*10^15

[TruthIsAll]

53. But JFERN, the 2% is the Exit Poll MOE.

You can't just use the standard polling MOE.

The whole point is that Exit polls are at least twice as accurate as the standard 3% poll MOE.

Even 2% is generous. Historically, its closer to 1%.

[lessthanjake]

55. The BIG PROBLEM is this...

There is more than one explanation for this situation.
There is that there was fraud.
However there also is the idea that the exit polls simply polled too many minorities (ie they went to too many minority areas).
Theres also the idea that the exit polls were done before the time when most republicans vote (exit polls were done at 4 and republicans come at like 6 mostly).

The second two sadly seem more credible and easily explainable to me.

[Atman]

56. Where do you get those times?

Republicans historically vote at 6? All of them?

I worked the polls...there was a constant, steady stream of traffic ALL DAY. There were 10 hour lines in some place. That hypothesis seems far less likely to me than the statistical analysis, as does the likelihood that during THIS election (and only elections involving George W. Bush, historically) that they just happened to poll too many blacks. THOSE are stretches. The analysis seems far more likely, imo.

[mhr]

57. Those Are Some Mighty Big Assumptions About When People Vote

At best they are presumptions at this point.

If the Exit Polling data will tell the tale then why are the keepers of the exit poll data so unwilling to share their data?

[Faun Otter]

62. Time period weighted sampling

Sorry - exit pollsters have been there and dealt with the problem years ago.

Faun

[bemis12]

60. Is the number of states

beyone the MOE now 22? Man, every time you compute this there's more of them. There were 16.

This needs to stop or ALL of them will be outside the MOE by Christmas.

[earth2chuck]

63. Access to Hack it, then Excel to calculate it...Nice Symmetry there :-)

Nice analysis.

Chuck

[Protect The Vote]

74. TIA, I love your posts

I've been working on looking at historical exit polling (2000 and 2002 congressional) to use to give some historical perspective to how impossible your 2004 results are. I have some questions:

1) Where did you get the data for the 2004 exit polls? Can you give me a link to a primary source?

2) Do you have any idea where I can get the *raw* exit poll data from historical elections? I've been using CNN's and MSNBC's old data, and there are differences between them, so they must have used different weighting of the raw data. I've looked at ICPSR's data at http://webapp.icpsr.umich.edu/cocoon/ICPSR-STUDY/03527.xml but it looks like I would have to be a member of ICPSR to get the weighting data.

I'm a data-crunching machine and I new some raw data to crunch!

PTV

[Name removed]

76. Deleted message

Message removed by moderator. Click here to review the message board rules.

[Name removed]

78. Deleted message

Message removed by moderator. Click here to review the message board rules.

[Name removed]

80. Deleted message

Message removed by moderator. Click here to review the message board rules.

[Name removed]

82. Deleted message

Message removed by moderator. Click here to review the message board rules.

[Name removed]

83. Deleted message

Message removed by moderator. Click here to review the message board rules.

[Name removed]

84. Deleted message

Message removed by moderator. Click here to review the message board rules.

[bigmustelid2]

85. I see - because I have 21 posts

that makes you less wrong about exit polls never having been inaccurate before 2000? I can't quite follow that leap of logic.

[TruthIsAll]

77. I can't help you with raw data. I got my data from the various

postings at DU (these are primarily 4pm exit poll results).
Check threads by althecat in the voting forum.

[Protect The Vote]

88. Thanks, TIA

No one has the 2004 raw data, except Mitofsky. Hopefully Mitofsky will release the data this week in response to Coyers' request.

The 4pm exit poll was the info I needed. I'll check the old threads.