Fraud question: Was the exit polling outside the margin of error?

[usregimechange]

[nadinbrzezinski]

1. Some indeed were

Here you go


In the exit polls for 18 Battleground states taken around 4pm,
Kerry's unweighted average was 50.67% vs Bush 48.20%.

Two (2) states (CO and MO) moved in Kerry's direction in the
final vote (each by 1%).

In four (4) states the exit polls were EXACTLY right.

Twelve (12) states moved in Bush's direction in the final
vote.

Kerry had a 99.96% probability of getting at least 50% of
the vote.
He ended up with 48.87%.

The odds were not with John that night.
Just bad luck, I guess.

Probability of Kerry majority:
=NORMDIST(50.67/(50.67+48.2),0.5,0.0037,TRUE)

Exit Poll 4pm Actual Results
Kerry Bush Diff Kerry Bush Diff BushGain
1 AZ 45 55 -10 45 55 -10 0
2 LA 43 57 -14 42 57 -15 1
3 MI 51 48 3 51 48 3 0
4 IA 49 49 0 49 50 -1 1
5 NM 50 48 2 50 50 0 2
6 ME 55 44 11 53 45 8 3
7 NV 48 49 -1 48 51 -3 2
8 AR 45 54 -9 45 54 -9 0
9 MO 46 54 -8 46 53 -7 -1
10 IL 55 44 11 55 44 11 0
11 WI 52 47 5 50 49 1 4
12 PA 53 46 7 51 49 2 5
13 OH 51 49 2 49 51 -2 4
14 FL 50 49 1 47 52 -5 6
15 MN 54 44 10 51 48 3 7
16 NH 58 41 17 50 49 1 16
17 NC 48 52 -4 43 56 -13 9
18 CO 46 53 -7 46 52 -6 -1

average 50.67 48.20 2.47 48.87 50.20 -1.33 3.80

Prob = 99.963%
assume 3% Moe

n= sample size = 18000

MoE=1.96/(2*sqrt(n))
Std=.5/sqrt(n)

MoE 0.0073
Std 0.0037



Oh and also look for Greg pallast, and others.. this is not our imagination the fraud happened, and as liong as we have evoting we can run Jesus Chirst Repetant and they will STILL win.

[barackmyworld]

2. it's not a random sample

there is nothing that can be called a margin of error, because exit polling is not done within the requirements of statistical analysis.

[Woody Box]

3. Nonsense

there is nothing that can be called a margin of error, because exit polling is not done within the requirements of statistical analysis.

I fear you don't know what you're talking about. What do you mean by "requirement of statistical analysis"?

Even if you ask not more than ten people, it is possible to determine the margin of error - it would be pretty big, of course.

[SoCalDemocrat]

5. Excuse me?

I think 1500 persons is sufficient for the U.S. voting population to be statistically significant.

Alot more than 1500 persons were polled.

[blurp]

4. Sampling error is +/-4%

http://www.exit-poll.net/faq.html#a10

"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. "

Keep in mind that's just the sampling error. Projections are made with additional information that induces it's own error.

[Woody Box]

6. Be careful

This +-4% is a relative error, it refers to the percentage of the respective party.

So, if the exit polls predicted 50% for Kelly in Florida, a result from 48% to 52% (+-2 percent of 50%) was to be expected.

It turned out be 46.5%. Low enough to suspect manipulation.

And we haven't spoken yet about New Hampshire.