Any mathematician/statistician out there who believes we have

[Emillereid]

a voter fraud case? I keep looking at the data as presented, but my statistics knowledge is limited -- besides my expertise is psychological and nutritional data and I don't know the behavior of voting data at all. So what I'm looking for is a thread to take a cold, scientific look at this stuff. Is there anything really curious or weird about the voting patterns -- or is the stuff that looks goofy all spurious?

Another thing -- I know that if data begs too many questions even though everything can be explained -- just the sheer number of explanations necessary to cover the data is indicative of something amiss itself. The old Ptolemy epi-cycles thing. In other words the sheer presence of too many anomalies is itself anomalous.

[tuvor]

1. You might find this interesting.

http://www.consortiumnews.com/2004/110904.html

[crimmer]

2. A simple message for you all

Honestly, kids, can we all just accept that GW got re-elected....I mean, get a life!!!!!

[mountebank]

3. Excellent first post.

You'll make a lot of friends here.

[DELUSIONAL]

4. How obvious can a freeper be??

1. Bushie wasn't "elected" the first time so this isn't a re-election.

2. Bushie wasn't "elected" this time -- massive vote fraud took place --

Biggest indicator -- if what we are seeing is merely "errors" then about 50% of the errors should have been in Kerry's favor BUT all the errors were in bushie's favor.

3. the only way bushie can win is to cheat.

4. The GOP worked to suppress the vote

5. the Democrats worked to get out the vote and register new voters --

6. As a psyop operative this freeper fails --

[crimmer]

6. so easy...

to piss dem's off.....

[Lilli]

10. Who's pissed?

I'd just like you to be a bit more creative if youre gonna troll. We have to have some standards ya know?

[tuvor]

7. You're welcome to leave.

If you're not interested, don't waste your time here. Or mine.

[Runcible Spoon]

8. hey sport!

enjoy your short stay!

[tavalon]

17. Cute

I've never actually gotten a chance to see a real one - the mods always seem to get rid of them so quickly.........

[EST]

22. Nope!

They stole too much of my life.

[On the Road]

5. This is NOT a Statistics Question

The open issue is whether Bush voters responded differently to exit pollers than Kerry voters. As long as this is an alternate theory, no statistical analysis can prove fraud.

The key is the history of exit polling. Zogby has gone on record as saying that exit polls are never this far off from actuals. I hope as this issue develops he can quantify that in a persuasive way.

[tuvor]

9. Exit pollers choose at random.

Every 20 or so voters. Aren't you assuming that the number of Kerry voters polled = the number of bush voters polled?

[Emillereid]

12. One can't assume the numbers are equal ahead of time.

Presumably the pollers asked people using some method like a random numbers table or some such method of random sampling. The question is whether a given demographic was over represented for the sampling. And if it was, was it consistently over represented in every sample in the same way and for every state. Were other demographics over or under represented for particular sample and in the same way for every state. What are the odds of this and is this consistent with polling behavior for other times and places, etc.

[On the Road]

16. It's a Response Variable That's Being Questioned

Sampling or random error is a red herring. For example, if you used an exit poll to measure how many people cheat on their spouses, your result would probably not match reality. And nothing in your design or sampling could give you a correct answer.

There may be something to the response issue. That's what makes it so difficult to convincingly argue. The best avenue would be to look at previous exit polls in similar elections where strong response effects would be expected.

Xogby believes the exit polls. I hope he can make this kind of argument.

[Emillereid]

11. But couldn't the particular exit polls used not be particularly

representative -- for example what if more of one demographic was polled for a particular exit poll in a way that was not representative of the whole population. There been some talk that women were over represented for instance for the exit polls that the media reported ( 4 PM) and that we all relied on. Note -- I'm not asserting this as true, just using it as an possibility.

A MIT statistician "Anick reasons that there are four possible causes of the “Bush gains.” (1) Significantly greater lying or refusal to speak to pollsters in Bush voters versus Kerry voters; (2) Consistent/systematic errors in weighting demographic groups; (3) A surge of Bush voters after 4 p.m., in all states; (4) Systematic tampering/hacking of reported vote totals, in Bush’s favor." http://www.bluelemur.com/index.php?p=405

Note that one of the possible explanation is consistent/systematic errors in weighting demographic groups -- which actually might go along with explanation # 3.

What I would like to know is whether the exit polling data was correct for any state? Was the exit polling data only off for the so called swing states???

[OrangeCountyDemocrat]

14. Exit Polls

They were off the most in the states where electronic voting or optical-scan ballots were used. In the paper only states, they were more or less right on the money, w/in margin of error. In e-voting states, however, they were off anywhere between 4-15%, which is well outside margin of error for exit polls.

[bigmust]

21. Not according to the MIT professor

in the following article (of course, he *could* be a "freeper"):

http://www.bluelemur.com/index.php?p=405

"...
The analysis, conducted by former Associate Professor of Mathematics David Anick, also ruled out any significance of a variance between electronic balloting and paper ballot states, which RAW STORY reported last week.

In fact, the non-electronic voting states of New York and New Hampshire had higher gains for President Bush than states in the exit polls using some electronic balloting: Arkansas, Colorado, Florida, Iowa, Ohio, New Jersey, New Mexico, Nevada and West Virginia.

Moreover, the analysis found that states using optical scan technology to read paper ballots were not more likely to have exit poll variance than other states. Because New York, which uses lever balloting, had such a large variance, the optical scan variance is within the threshold of being statistically explained by chance...."

[EST]

24. Waitaminit!

These "facts" disagree with all the other stats I've been reading!

[tuvor]

15. Exit polling data correct for any state?

>>What I would like to know is whether the exit polling data was
>>correct for any state? Was the exit polling data only off for the
>>so called swing states???

I no longer have a link handy (although I probably found it on DU, BuzzFlash, or possibly BartCop), but I believe that there were few, if any, surprises wrt the exit polls in counties where the votes had some sort of paper trail--optical scanners, butterflies, etc.

[On the Road]

19. Yes, the Early Exit Polls Were Representative

of expected turnout. That's all you can do until after the election.

If actual turnout is significantly different, the weightings have to be redone. More elderly people showed up than in 2000. That's one factor which favored Bush. If they were reweighted simply to match the official count, that's spurious. But given the changes in turnout, the simple fact of doing a reweighting should not be controversial.

There are also response variables. Exit polls are only good if the responses match actions. We don't know that for sure. It sometimes doesn't happen.

[jsamuel]

13. John Zogby says Statistics can prove Votergate in court

"There's a huge difference between polling what WILL happen and polling something that has already happened. The reliability of polling something that has already happened is highly reliable vs. predictive polls, like Gallup or Zogby, which is very risky. The reliability can be, not plus or minus 4 percent as we see with predictive poplls, but rather a much more reliable plus or minus one half or one tenth of one percent with exit polls, because those are based on asking people who already voted. I would even say that if the exit polling were done in the key precincts of Florida and Ohio, which it was, then these results should be practically “bullet proof.”

It is important that people know how accurate random sampling of historical events can be in order for them to understand how unlikely it is that the exit polls were wrong. So if you want to fight the battle correctly, you must get more statisticians and forensic accountants involved as well as the lawyers. These statisticians can show with great credibility the probability of manipulation within the computer programs used for counting the ballots. They do this kind of work all the time to uncover fraud based upon computer manipulation in commercial and corporate activities. And these types of expert analyses are admissible in a court of law. The problem with all of this is determining who is going to fund such an investigation. Where will the money come from? Perhaps the Kerry/Edwards campaign fund has some surplus that can be used. It is possible that the DNC has some excess funds. How about the 527s and PACs who spent millions on ineffective political ads, coming up with a few million? In addition, who is going to lead the process of getting this done? This kind of an effort requires solidarity along with an organized coordinated effort. It's easy to come up with the forensic and technical people to get this done, but we need a strong leader and solidarity. Leadership and funding-- these are the two real challenges that must be dealt with in the coming days. We have a Watergate story here that could give the media a post election explosive news story that could make the 2000 Florida vote debacle look like small potatoes. We need to get the media to see that votergate 2004 is huge news and we need to quickly fund the investigation and get Democratic leaders behind it.

Sheldon Drobny is CPA and Venture Capitalist and co-founder of Air America Radio.

(11/9/2004)
- By Sheldon Drobny, Op-Ed News "
http://www.zogby.com/Soundbites/ReadClips.dbm?ID=10385

[tuvor]

18. Why do the Dem leaders always seem to need to be prodded to do anything?

"We need to get the media to see that votergate 2004 is huge news and we need to quickly fund the investigation and get Democratic leaders behind it."????????

I'm starting to think BartCop's totally right.


"The Democrats don't mind losing. If the GOP can steal elections and the Dems don't care, why should they stop stealing them?"--BartCop

[jsamuel]

20. I don't know... I even sent an email to

Keith O' at countdown. I asked him if he still has that 99,000 dollars from the O'Rielly thing.

[Oak2004]

25. Just over a week ago I thought I was fighting for the Democrats

against the Republicans (not as a Democrat, because I'm a Republican in exile who is now registered as a VT Progressive).

Now I'm beginning to think I may be fighting for democracy against the Democrats (and, of course, Republicans).

And I'm also beginning to think that the next national elections, if I survive, I'm going to go Green. Pragmatism is clearly not enough to resist fascism: integrity and determination count, too.

[Rawls vs Nozick]

23. Not Zogby's words

That is a quote from an article which is listed on the "Zogby in the Media" page at Zogby's company's website.

The person who wrote it is Sheldon Drobny, as it says in the very part you quoted!

-RvN-

[jsamuel]

26. Woops...