INDEPENDENT Mathematicians, statisticians et al: Critique the analysis

[TruthIsAll]

To believe that Bush won the election, you must also believe...
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x22581

18 Battleground State Exit Polls:
The Probability that Kerry would get over 50% was 99.998%.
He got 48.87% of the votes.
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x29275

REVERSE THE MEDIA SPIN:
Kerry's 2-Party% vs.Bush- Exit Polls vs. Actuals
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x31588


Exit Polls vs. Actuals:
Who do you believe-CNN or your lying eyes?
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x26387


PROBABILITY KERRY WOULD LOSE BOTH OHIO AND FLORIDA:
(BASED ON THE EXIT POLLS): 1 OUT OF 667 (.15%)
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x27862


MASSIVE FRAUD!
ANALYSIS VINDICATED BY A FORMER MIT MATH PROFESSOR
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x32899

187 MILLION TO ONE:
The odds that 7 out of 18 Battleground states would deviate from Exit Polls beyond the Margin of Error - all in favor of Bush.
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x38892


250 MILLION TO ONE:
PROFESSOR FREEMAN AT THE UNIV. OF PENN. CALCULATED THE ODDS THAT ACTUAL VOTE DEVIATIONS FROM THE EXIT POLLS ARE NOT DUE TO CHANCE.
http://www.dakotatechnics.com/downloads/Steve_Freeman.z...
DU thread to the above link:
http://www.democraticunderground.com/discuss/duboard.ph...

Scoop: 47 State Exit Poll Analysis Confirms Swing Anomaly
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=203x38567

Statistical proof the election was rigged. IMPORTANT! Please read!
http://www.democraticunderground.com/discuss/duboard.php?az=view_all&address=104x2682466

[bones_7672]

1. In the end, it wont be the statisticians, etc. that matter

what will matter is the number of votes certified by the individual secretaries of state. No state gov't is going to act on what an academic writes up in some paper, they'll only care about the votes for Bush and the votes for Kerry.

[bemildred]

2. OK, I'll try.

What you have here is statistical evidence, enough to create
the suspicion that something is not right, but not PROOF.

Enough to demand that the votes be counted carefully, all of
them in all categories, to demonstrate that the voting
system works accurately, and incidentally to determine who is
elected. This seems to be what is being attempted now.

If, aside from all this, one can come up with testimony of fraud,
collusion, conspiracy, etc. or hard evidence of the same in the
form of written documents, then one can look into more rewarding
avenues like criminal process etc.

[bones_7672]

3. But, at the state and county level ...

the BOEs will say that if a state falls into the area of a mandatory recount (here in Ohio it is .25%) or a paid recount (in Ohio, $10 per precinct), they will do a careful recount. But barring those two events, no white paper is going to budge a BOE to do anything.

[TruthIsAll]

6. I asked for a critique to confirm the mathematics.

You know, the normal distribution, the binomial distribution, the Poisson distribution et al.

[bemildred]

12. Math really isn't the issue.

The math is simple, any cheap calculator can do it for you.
The data is what matters. Garbage in, garbage out. I stick by
my original assessment.

[barackmyworld]

4. Exit polls can't be used in statistical analysis

They are not a random sample. It does not fit the requirements of statistical probability tests!

[TruthIsAll]

5. And your credentials, sir? Back up that statement.

tia

[barackmyworld]

7. first, I'm not "sir"

I am a (female) Harvard student, and I've taken statistics classes. Tests to find the margin of error, or probability that two numbers are significantly different, etc all have conditions. For example, the population has to be much larger than the sample size (exit polls are fine for that). It also has to be a random sample. Yes, you can do stat tests on a non-random sample, but they won't tell you much. I'm not contesting that there are discrepancies, or that they might be large. But stat tests are not appropriate to show that. Many stat tests in areas of sociology, medicine, and other areas are discounted because there was a bias in the sample.

edit: I did some googles, and I can't find any statistical test that could be used in this case that doesn't require a random sample. Also, I want to reinforce the point that you can use stat tests here, but there is no way to judge the accuracy of the results. You can do statistical inference about the United States from a random sample of two people, but it won't mean anything. Let's say you asked those two people if they liked pink or blue better, and you wanted to compare that to the national statistic that 50% of people like pink, and 50% like blue. If by chance, one of those people liked pink, and one liked blue, it would mean that your test "is accurate," but there is ALMOST as great of a chance that they would both like pink, or both like blue. Then, your study would show "a massive difference in pink vs. blue preferences!" This is an example where if you violate one of the requirements for inference (usually you need 30 people for a z-test, 10 for a t-test if my memory serves me correctly), your results are not mathematically accurate.

[TruthIsAll]

8. I suggest that you link to what the two professors have to say.

Sorry for the gender glich.

[barackmyworld]

9. the links are broken

I'd be happy to read it, if someone can fix those two links

[TruthIsAll]

10. Sorry, Maya. Until I fix the last link,please look at the others.

tia

[TruthIsAll]

11. Maya, try this link

http://www.buzzflash.com/alerts/04/11/ale04090.html