National Exit Poll sample: Nov 3, 12:23AM ; Odds: 1 out of 547 million.

[TruthIsAll]

This analysis is very similar to that of Ron Baiman.
Baiman calculated the odds of the Kerry shift (-2.56%).
For completeness, I calculate the odds of the Bush shift (+3.01%).

National Exit Poll Sample: 13,047 voters
Downloaded by: Jonathan Simon at 12:33 am.

Note: Exit Poll Data and assumptions are given by Edison/Mitofsky, which are clearly displayed at the bottom of the Washington Post web site graphic shown below.

The date of the graphic: Nov 3.

The site is no longer available, but if you care to see the original URL, just right click on the graphic and click on Properties.

But as I said, the link no longer exists.

These are the KEY assumptions, as stated by Edison/Mitofsky:
1) It is a randomly selected sample.
2) The Margin of Error is 1.0%

The voting split:
Female: 54%
Male: 46%

The split was consistent with earlier samples from 4pm and 7:33pm.
This is how they voted:

Women voted for Kerry: 54%-45%
Men voted for Bush: 52-47%

Since there were more women voting than men, Kerry had the advantage.

Here's the calculation of the national percentages based on the gender split:

Kerry = .54*.54+.47*.46 = 50.78%
Bush = .45*.54+ .52*.46 = 48.22%

Kerry led the national exit poll by 2.56%.
But Bush won the vote by 2.80%.

Exit Actual Diff
Kerry 50.78% 48.43% -2.35%
Bush 48.22% 51.23% 3.01%
Diff 2.56% -2.80% -5.36%

As stated by Mitofsky/Edison, the MOE = 1%.
Therefore, the population standard deviation is:
StDev = MOE /1.96 = 0.00510

This means that 95% of the time we would expect that the Bush actual vote would fall between 47.22% and 49.22%, within 1.0% of his exit poll sample mean of 48.22%.

What is the probability that the Bush tally would exceed his exit poll sample mean by 3.01%, and rise from from 48.22% to 51.23%?

Probability = NORMDIST(0.4822,0.5123,0.0051,TRUE)
Probability = 0.00000000183

The odds are 1 out of 1/.00000000183 or

**************** 1 out of 547,044,797 ****************

............................................................

[PROGRESSIVE1]

1. kick

[OrangeCountyDemocrat]

11. So It Is Possible

I don't know. Is 547 Million To 1 really beyond a reasonable doubt? Unbelievable!

[TruthIsAll]

24. THE ODDS: CONSIDERING 0.5% ROUNDOFF ERRORS

The exit poll percentages are rounded to the nearest 1%.
It would be preferable to show at least 1 decimal place for
greater computational accuracy.

Therefore, I have also calculated the odds assuming 
1) a Best Case scenario for Bush (his numbers rounded UP
0.5%), 
and 
2) a Worst Case scenario (his numbers rounded DOWN 0.5%). 

The 0.5% adjustments were made to the female/male split as
well as to Bush's percentage for each.	
					
					
THIS IS THE BASE CASE CALCULATION FOR THE EXIT POLL DATA SHOWN
IN THE GRAPHIC WHICH WAS ROUNDED TO THE NEAREST 1%: 				
	Kerry = .54*.54+.47*.46 = 50.78%			
	Bush = .45*.54+ .52*.46 = 48.22%

These parameters were entered into the normal distribution
function:
Probability = NORMDIST(0.4822,0.5123,0.0051,TRUE)
(seethe original post).

............................................................
HERE ARE THE CORRESPONDING CALCULATIONS FOR THE BEST AND WORST
CASE SCENARIOS FOR BUSH, AFTER INCREMENTING INPUT PARAMETERS
BY THE +/-0.5% ROUNDOFF ERRROR.			
............................................................

WORST CASE: -0.5%
       Worst case	Base Case		
Split	Male	45.5%	46%		
	Female	54.5%	54%		
					
Vote%	Male	51.5%	52%		
	Female	44.5%	45%		
					
	Weight	47.69%	48.22%		
					
Probability = NORMDIST(0.4769,0.5123,0.0051,TRUE)				
WORST CASE PROBABILITY
	Prob	        Odds: 1 out of			
	1.82532E-12	547,849,842,147			
..............................................................					
					
BEST CASE: +0.5%					
       Best Case+.5%	base case		
Split	Male	46.5%	46%		
	Female	53.5%	54%		
					
Vote%	Male	52.5%	52%		
	Female	45.5%	45%		
					
	Weight	48.69%	48.22%		
					
	Probability = NORMDIST(0.4869,0.5123,0.0051,TRUE)				
BEST CASE PROBABILITY
	Prob	        Odds: 1 out of			
	3.02063E-07	3,310,571			

[TruthIsAll]

26. CALCULATION FIX: BEST CASE

The calculation was wrong:
Bush% for Best case should be: 48.76%

 48.76% = .465*.525 + .535*.455

BEST CASE	+0.5%	base
Split	Male	46.5%	46%
	Female	53.5%	54%
			
Vote%	Male	52.5%	52%
	Female	45.5%	45%
			
	Weight	48.76%	48.22%
			
	Probability = NORMDIST(0.4876,0.5123,0.0051,TRUE)		
	Prob	         ODDS:	1 OUT OF
	6.09049E-07	1,641,904	

[Pachamama]

2. There is not one doubt in my mind that Kerry won...

Eventually, it will be shown and proven...sadly, not in time for us to save the world from the Bush Administration Tsunami...

:cry:

[pstans]

3. Bu$h just won the lottery

These #'s need to get circulated cause that is one heck of a longshot.

[Kansas Wyatt]

4. Shrub allegedly won two lotteries on the same night.

[TruthIsAll]

5. The state probabilties are much more unlikely than this. n/t

tia

[TruthIsAll]

6. The odds are much lower for 16 states beyond the MOE...

1 in 13.5 trillion. Same analysis.

[ClintCooper2003]

7. Did someone copy and keep this? I can't for some reason.

[dzika]

8. TIA - Did you read Conyers' Report today?

I just skimmed it for specific things but I didn't look close. Did they provide a statistical analysis of the exit polls? If so, did you agree with it?

[TruthIsAll]

9. I have not read it. But I will soon.

Hopefully, this analysis, being concise, will jump out at people.
Eyes glaze when there is too much to assimilate.

Baiman and Freeman do the academic stuff. We need that.

But we also need something easily digestible, yet robust enough to
deflate those naysayers who only seek to spread fog.

What is interesting is that all the statistical analysis I have seen from others at DU to Freeman to Baiman agree:

The odds range from 1 in 50,000 (assuming conservative cluster polling to 1 in 13.5 trillion or more, if you assume reasonable MOE's.

The fact that Mitofsky claims a 1% MOE for the National 13,047, is a powewrful statement for fraud.

Thanks to Jonathan Simon for capturing the data. Without his downloads, we would have nothing.

No matter where you look, state exit polls or the national exit poll, the numbers are telling us there is no question that this election was stolen.

[Carolab]

10. TIA

Do you ever submit your own analyses? I have included your work in many e-mails, etc. I think it is very important and Conyers, et al should have it.

[TruthIsAll]

12. No, I do not. I'll leave that to Baiman, Freeman and Berkeley.

In fact, I'm sure those guys are influenced by what I have posted.

These posts get picked up at many Blog sites.
I prefer to let them spread it around.

[dzika]

14. Yep. I pulled an essay off the newsgroups the other day

that cited you as a source.

Now, there is something to google:
http://www.google.com/search?hl=en&ned=us&q=truthisall&btnmeta%3Dsearch%3Dsearch=Search+the+Web



Off topic, but I just noticed that Cameron Kerry released a new letter. It has been posted.

[tritsofme]

15. Mitofsky says the MoE was 3%

The fact that Mitofsky claims a 1% MOE for the National 13,047, is a powewrful statement for fraud.

What is the Margin of Error for an exit poll?
Every number estimated from a sample may depart from the official vote count. The difference between a sample result and the number one would get if everyone who cast a vote was interviewed in exactly the same way is called the sampling error. That does not mean the sample result is wrong. Instead, it refers to the potential error due to sampling. The margin of error for a 95% confidence interval is about +/- 3% for a typical characteristic from the national exit poll and +/-4% for a typical state exit poll. Characteristics that are more concentrated in a few polling places, such as race, have larger sampling errors. Other nonsampling factors may increase the total error.

http://www.exit-poll.net/faq.html#a15

And I think Mitofsky's own website is more credible than some obscure graphic on the Washington Post's website.

[TruthIsAll]

16. You keep coming back and conveniently ignore the graphic. Buh-bye.

This is a NATIONAL Exit Poll of 13047.

PLEASE READ THE NOTES.

You are quoting what they said about STATE POLLS, which typically sample 1000. For 1000, the MOE is 3.1%

PLEASE READ THE NOTES.

Since, by their own admission, this was a randomly-selected sample, you can figure out the MOE by yourself.

Let's figure it out right here.
If N= the number sampled, the MOE = 1/sqrt (N)
Since N= 13.047, MOE = 0.88%.
That is damn close to the 1% Mitofsky claims here.

PLEASE READ THE NOTES.

I hope this is the last time you try to "correct" me.

PLEASE READ THE NOTES.

[tritsofme]

17. You keep pointing to some obscure graphic as if it is Gospel

I think I'll take Mitofsky's own website when I make my determinations.

[TruthIsAll]

18. Obscure graphic? Hmmm... Obscure formula, too, I suppose..

...

[tritsofme]

19. I know how margin of error is determined

and I know the MoE for a sample of 13,000 should be about 0.88%, but I wonder why Mitofsky seemingly thinks so little of his own polling that he says differently.

[TruthIsAll]

21. He had it right here, though. BTW, the link works. Its still up.

Better let him know, so he can get it taken down before anyone sees it.

[Bill Bored]

13. The link works

<http://www.washingtonpost.com/wp-srv/politics/elections/2004/graphics/exitPolls.html>

and as I've said, all you have to do to put Bush in the game is to re-weight the party affiliation (turnout) to D/R 37/37 from D/R 38/35. This is how Mitofsky did it.

So to prove whether these polls were right or wrong, just find the CORRECT party turnouts nationwide from another reliable source, or particularly in the West where this weighting change was greatest.

[TruthIsAll]

20. Thanks, Bill. It's a SMOKER, no? n/t

.

[TruthIsAll]

22. Just in time for D-Day. Another mathematical impossibility. n/t

.

[Stevepol]

23. TruthIsAll, I'm curious about the 02 GA results.

Have you done any statistical regrssions on this? I've tried to find out the exit polls but they were pulled off the internet soon after the election, apparently because they were so wildly innacurate. The guy who ran the exit polls, however, was interviewed in a newspaper report afterwards and claimed that his polls were well w/i the MOE in every other race where he did such polls. He gave examples. I do have the pre-election polls that were done. Tho I know pre-election polls are less reliable than exit polls, I'm still very curious about the odds. Here are the numbers for Roy Barnes' and Max Cleland's races.

The poll asked 800 likely voters who they would vote for. In the governor's race, the poll had 409 (51%) for Barnes , 320 (40%) for Perdue, 71 (9%) for Other. In the actual results, 937,062 (46%) for Barnes, 1,041,677 (51%) for Perdue, 47,122 (3%) for Other. TOTAL VOTE: 2,025,861

In the senate race, the poll had 392 (49%) for Cleland, 352 (44%) for Chambliss, 56 (7%) for Other. The actual results had 931,857 (46%) for Cleland, 1,071,153 (53%) for Chambliss, 26,981 (1%) for Other. TOTAL VOTE: 2,029,991

I've always thought this election was the most transparently fraudulent I've ever seen and maybe in American (world?) history and yet nobody did much more than take a few moments to pause before moving on to the next news item. It was the first time DREs (Diebold touchscreens) were used w/o any possiblity of audit or recount and w/ multitudes of anomalies, as well as testimones by the parties themselves as to patching after certification. Neither Cleland nor Barnes even mentioned the outrageous numbers or any problems with the voting, as if this is the kind of thing to be expected in an election. And news guys like Mark Shields just paused a moment before getting on to the next item.

[TruthIsAll]

25. LOOK HERE

http://www.democraticunderground.com/discuss/duboard.php?az=show_topic&forum=104&topic_id=85732