Democratic Underground Latest Greatest Lobby Journals Search Options Help Login
Google

Naysayer Hobson's Choice: Final NEP or rBr? Take your pick.

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
This topic is archived.
Home » Discuss » Topic Forums » Election Reform Donate to DU
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 12:48 AM
Original message
Naysayer Hobson's Choice: Final NEP or rBr? Take your pick.
Edited on Thu Jun-23-05 01:12 AM by TruthIsAll
Let's continue our discussion of the 43%/37% Bush/Gore
weighting split in the How Voted in 2000 demographic of the
Final National Exit Poll. Bush won the poll (and the vote) by
51-48%.

To review, according to the poll, 43% of all 2004 voters were
former Bush 2000 voters and 37% of 2004 voters were former
Gore voters.

Gore won the popular vote in 2000 by 50.999mm to 50.456
million for Bush.

Some, but not all of you have stipulated to the mathematical
fact that for 43% of 2004 voters to have been Bush 2000 voters
was an impossibility, since 43% of the 122.3 million who voted
in 2004 is 52.59 million. And yet we know that Bush only got
50.456 million votes in 2000.

So now you have a choice:

1) You can argue, against all mathematical logic, that the
final national exit poll was correct; that 43% is a valid
weighting multiplier for Bush and 37% is a valid weighting
multiplier for Kerry. And therefore the Final Exit Poll
correctly matched to the recorded vote count, as reflected by
the 51-48% Bush exit poll win. 

or

2) You can continue to hypothesize the reluctant Bush
responder theory. Of course, by doing so, you must reject the
43%/37% split, since that weighting mix implies that Bush 2000
voters outnumbered Gore 2000 voters by a whopping six percent
margin.

So which is it?

Do you claim that Bush won the final exit poll (13660
respondents) and that the 43%/37% split (although
mathematically impossible) is still a valid weighting mix?

Or do you reject the final exit poll and promote the rBr
hypothesis as a possible explanation for the exit poll
discrepancies? 

You cannot have it both ways. 
Take your pick.

43/37 vs. rBr. 
Impossible vs. implausible.

*******************************************************
HERE ARE THE 13047 AND 13660 HOW VOTED IN 2000 WEIGHTS AND
PERCENTAGES 
 
The maximum possible percentage of Bush 2000 voters who could
have voted in 2004 is 39.82%.

Bush 2000 voters: 50.456 million
Bush 2000 voters still alive = 48.69mm

Total 2004 voters: 122.3 mm.

Maximum Bush 2000 voters as a percentage of Total 2004
voters: Bush 2000/Total 2004 = 48.69/122.3 = 39.82%
The same calculation for Gore voters = 40.25%



Now lets look at the National Exit Poll:

Who did you vote for in 2000?	

SCENARIO I:
13047 respondents: 12:22am
Kerry wins easily- even with an IMPLAUSIBLE 41% Bush/39% Gore
split

	Mix   Bush	Kerry	Nader	Bush	Kerry	Nader
No	17%	41%	57%	2%	7.0%	9.7%	0.3%
Gore	39%	8%	91%	1%	3.1%	35.5%	0.4%
Bush	41%	90%	10%	0%	36.9%	4.1%	0.0%
Other	3%	13%	65%	16%	0.4%	2.0%	0.5%
	100%				47.38%	51.23%	1.21%

Probability of Bush going from 47.38% (poll) to 50.73%
(vote):  1 in 38,498,885,514

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

SCENARIO II:
Final Exit Poll (1:25pm)- 13660 respondents:
BUSH WINS, even though 43% is MATHEMATICALLY IMPOSSIBLE

      MIX	Bush	Kerry	Nader	Bush	Kerry	Nader
NO    17%	45%	54%	1%	7.7%	9.2%	0.2%
Gore  37%	10%	90%	1%	3.7%	33.3%	0.4%
Bush  43%	91%	9%	0%	39.1%	3.9%	0.0%
Other  3%	21%	71%	8%	0.6%	2.1%	0.2%
      100%				51.11%	48.48%	0.78%


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

PLAUSIBLE SCENARIO III:
Using maximum possible Bush/Gore turnout weightings based on
2000 voters still alive to vote in 2004 (122.3mm total votes),
Kerry wins in a  landslide: 

Kerry	63.89mm (52.24% 
Bush	56.77 (46.42%)
Nader/Other 1.49 (1.22%)


      Mix	Bush	Kerry	Nader	Bush	Kerry	Nader
No	17.00%	41%	57%	2%	7.0%	9.7%	0.3%
Gore	40.24%	8%	91%	1%	3.2%	36.6%	0.4%
Bush	39.82%	90%	10%	0%	35.8%	4.0%	0.0%
Other	3.00%	13%	65%	16%	0.4%	2.0%	0.5%
	100%				46.42%	52.24%	1.22%
							

Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 08:58 AM
Response to Original message
1. And why I am not surprised "our friends" have not responded?
Because this is the conclusion of the 130 post thread now dormant. It is the culmination of the analytic thread going through TIA's work. It is the final brick in the wall constructingn the case, undeniable at this point, of election fraud.

Excellent work.
Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Thu Jun-23-05 12:15 PM
Response to Reply #1
11. Dormant? Why is it dormant?
I have two unanswered posts to TIA and one to you that were in that thread before you made this post.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 09:37 AM
Response to Original message
2. I am not a naysayer
but I am not afraid to tell you when you are not making sense. Getting bored of it, yes, but not afraid.

I don't know what you mean by arguing that "the final national exit poll was correct," so it is hard to comment on that. I do suspect that Bush won the popular vote, and that the so-called "reluctant Bush responder theory" is substantially correct. So does that mean that I accept both choices 1 and 2?

No matter how many times you say it, you have not presented evidence to demonstrate that 43% was a "weighting multipler for Bush," whether valid or invalid. Do we agree that actually, the exit poll data were weighted to official returns, not to reported 2000 votes? If not, you will have to present evidence.

"that weighting mix implies that Bush 2000 voters outnumbered Gore 2000 voters by a whopping six percent margin."

No, it does not, and the reason has been explained to you many times: people are known to misreport their past votes.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 10:03 AM
Response to Reply #2
4. You say: "people are known to misreport their past votes"; you believe rBr
Edited on Thu Jun-23-05 10:16 AM by TruthIsAll
Apparently, you will say anything.

You will even contradict yourself.
You believe 43/37 in the final NEP yet you also believe rBr.
I'm sorry, that makes no sense.

Its not love and marriage. 
They go together like a horse and carriage.

But rBr and 43/37 do not.
They are contrary.
They are grounds for divorce.

But rBr does not mean having to say you are sorry.
It just means you can't have your cake and eat it, too.

You will grasp at any possible explanation, no matter how
contrary to human experience.
Your logic is faith-based.
You resort to any and every possible excuse.
Every assumption on your part is designed to cast doubt on
fraud.
Your logic is counter-intuitive.

You are defending the Pro-Bush position which you have
staked-out from the beginning. 
But that is ok.
That is why you are a naysayer.

You give Bush the benefit of every doubt.
Even while the vast majority of voting anomalies favor Bush.
But the silent scream of the numbers is irrefutable.

Just once, OTOH, surprise us.
Say one thing that is believable.
Say one thing that is plausible.

Say one thing that is not hypothetical faith-based pablum.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 10:22 AM
Response to Reply #4
5. "people are known to misreport their past votes."
Why is this not believable? why is this not plausible? why is this not, in fact, proven?

Why do you call me "pro-Bush"? why do you speak of "hypothetical faith-based pablum"? why do you not address the actual arguments? and why do you expect these tactics to persuade anyone?
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 11:01 AM
Response to Reply #2
8. OTOH: "Getting bored of it, yes, but not afraid."--then take a hike...
...enjoy nature, breathe in, breath out, ohmmmm.

This is a voluntary activity. You spend a lot of time on activities that "bore" you. What's you gig? Why do you do this? Where is the incentive?

This is the culmination of several days "debate" during which the OTOH clan has taken a pasting.

Just say yes, you're right TIA. This makes perfect sense.

Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 11:42 AM
Response to Reply #8
9. unfortunately, it doesn't make perfect sense
as you probably suspect, since you don't try to rebut my arguments either.

When I leave DU, it will not be uttering craven nonsense. I have a professional reputation to protect. Not to mention my self-respect.
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Thu Jun-23-05 12:13 PM
Response to Reply #9
10. Deleted message
Message removed by moderator. Click here to review the message board rules.
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 12:33 PM
Response to Reply #10
13. of course I have arguments
Edited on Thu Jun-23-05 01:30 PM by OnTheOtherHand
and the rest of this doesn't bear response. It boils down to the assertion that disagreement with TIA is objectively bad, no matter who is right. That may fly here, but it will not win the battle for election reform.

(EDIT: just for the record, I wrote "professional reputation," not "professorial reputation.")
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 01:36 PM
Response to Reply #13
14. Please point out your positions on election reform.
Edited on Thu Jun-23-05 01:42 PM by autorank
And don't try to smack me for responding to the statement YOU MADE on reputation. YOU BROUGHT IT UP.

Now, here is a point where you outlined your position on electoral fraud. Sifting through this post, you seem to agree massive fraud is possible. Since you portray yourself as a contributor here, what are the specific things you propose to prevent this?


------------------------------------------------------------------
OnTheOtherHand (270 posts) Sat May-21-05 06:19 PM
Response to Reply #141
142. honestly at this point


I'm not sure what I think, about the 2004 election. I think Bush probably won the popular vote (which leaves room for voter suppression, as we know happened). But I'm not arguing it, because there's a lot I don't know. I can explain the reasons why I'm not convinced that the exit polls prove massive fraud, but that doesn't mean that I am ruling out massive fraud. And since massive fraud is possible, we have a big problem whether or not it actually happened in 2004, so in a way I don't even care that much whether it did.

I bet someone is gonna misread that and jump down my throat. But you asked a fair question, and that's my best brief shot at answering it right now.

http://upload.democraticunderground.com/discuss/duboard...
----------------------------------------
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 01:56 PM
Response to Reply #14
15. in case you didn't notice
Edited on Thu Jun-23-05 02:27 PM by OnTheOtherHand
the DNC just released a report with excellent specific, and wide-ranging, recommendations for electoral reform.

I am not "smacking you," except if it counts as a smack to note that you ignored the content of my post, and apparently reacted merely to the fact that I dared to disagree with TIA. It does seem common that:

(1) TIA makes a post (often in a new thread) with the gist, "Evil naysayers! come bow to the power of my truth, or capitulate!" (I guess I should have put that in caps.)

(2) Someone cheers the power of TIA's truth.

(3) Someone else points out why TIA is actually wrong.

(4) "Someone" (or TIA himself) accuses "Someone else" of evading, or cheating, or "hectoring," or "obfuscating," or being an objective ally of the Bush administration.

This is tedious, yes. Hectoring, quite possibly. But not on my part, I think.

So if you are tired of having people argue with TIA, maybe you might suggest that he lay back just a little on the confrontations, and we might get more done. Or perhaps you could recommend another course of trying to explain to TIA that he is loudly, utterly wrong on this 43/37 business. Doesn't being loudly, utterly wrong seem like, umm, bad framing?

And remember: in just a few days I will be gone, TIA can claim victory in impunity (as far as I am concerned), and he will still be loudly and utterly wrong. Whatever. Your choice.
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 03:22 PM
Response to Reply #15
17. So your position is that of the DNC. Well we're 1/2 way there...
Edited on Thu Jun-23-05 03:27 PM by autorank
The DNC report was a work by new and old staff. It was remarkable that it was issued at all. Finally, five years after Florida 2000 they addressed the racial bias of election fraud and the on-the-ground problems. That report would not have looked the way it did without tremendous pressure from DU and other groups with, frankly, superior knowledge of the problems. The report is not perfect and more needs to be done. Recognition of that is ripe here and among other activist groups and the pressure will continue. Ultimately, the disagreements are not about you or TIA or even rhetorical and interpersonal styles, they are about pursuing the truth through logical analysis. I see no logic in what you present, nor do I see any position, other than an endorsement of a report that has real utility as a start of a process not a final product. The weight of the evidence and the balance of the debate are exemplified in the lead post of this thread and the work that preceded it. Address that. If disparaging remarks about the product are your main point, you've made those, time to move on. If you want to hang around and disparage, fine also but don't expect to do it with impunity. USCountsVotes.Org is in tatters, it would appear, or at least split in a way that distracts from it's credibility. I suppose it is time to move on.

On edit: Recall that the Conyers Report on Ohio was issued shortly after the election, the executive summary. This was the point at which DNC should have spoken both in terms of credibility on 2004 and in anticipation of 2006.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 03:49 PM
Response to Reply #17
19. I am sincerely confused.
You write,

"The weight of the evidence and the balance of the debate are exemplified in the lead post of this thread and the work that preceded it. Address that."

That is exactly what I have tried to do, to address the content of the lead post of this thread. I have discussed other work in other threads.

If you ever catch me running around DU randomly disparaging TIA, you have a beef. It has been more like the opposite, I would say.

But if you cannot see the logic in my objection to the lead post of this thread -- if you cannot see why I think it matters that people misreport their past votes -- then perhaps you could stop, think, consider that I conceivably might actually have a point, and ask a question. Or, failing that, consider that I conceivably might think I have a point, and not go out of your way to pile on.

It's a very small part of the work, but I feel that anything worth doing is worth doing right. When TruthIsAll is as willing to entertain challenges to his reasoning as to his mathematics, we will be better off.
Printer Friendly | Permalink |  | Top
 
anaxarchos Donating Member (963 posts) Send PM | Profile | Ignore Thu Jun-23-05 03:45 PM
Response to Reply #15
18. This has gone "ad hominem" BEFORE we even get to the debate...
Look, OTOH...

TIA is an easy target. He puts himself out there nearly every day. Your sniping doesn't have to be very good to get a shot off at him...

What do YOU think?

OK, the exit polls are wrong because the "how did you vote" question is exagerated in favor of Bush... Heard that already. Now, let's hear the rest.

The entire survey is interconnected. Is it your contention that there was more red shift among those that voted for Gore in 2000 then is reported in the exit poll? Are you arguing that new voters didn't lean as much to Kerry? Where's the hypothesis that we can test in other ways?

It really is your turn...


Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 04:17 AM
Response to Reply #15
29. No DeLay. The TRUTH is claiming victory RIGHT NOW
Edited on Fri Jun-24-05 04:17 AM by TruthIsAll
You have lost, OTOH.
FACTS always win.

In this thread I have supplied reams of supporting data.
You have supplied ZILCH.
You have not refuted one SOLITARY conclusion based on analysis
of these FACTS.

I see nothing from you except stubborn denial of all these
FACTS and numerous attempts to complicate what turns out to be
a very simple, straightforward mathematical analysis.

Its 3rd grade arithmetic with some basic algebra thrown in.

But I have just included in this thread a response to one of
your nay-saying brethren and have taken the analysis once step
further, beyond the level of a third grader. If one of your
poly sci students did this type of analysis, I'm sure you
would grade him/her quite well. 

It is a voter turnout sensitivity analysis. Kerry wins ALL 120
scenarios of voter turnout. I have deliberately set the
analysis to favor Bush (after all, he always gets benefit of
the doubt), by assuming 100% Bush 2000 voter turnout for each
scenario.

Yet Kerry wins them all.

Go figure.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 02:55 AM
Response to Reply #14
26. WE CARE, EVEN IF YOU DON'T...
Edited on Fri Jun-24-05 02:59 AM by TruthIsAll
YOU SAY:
And since massive fraud is possible, we have a big problem whether or not it actually happened in 2004, so in a way I don't even care that much whether it did.

WELL, WE CARE.
WE CARE VERY MUCH.

BECAUSE WE VOTED FOR KERRY.
AND IT WAS STOLEN FROM HIM.

WHO DID YOU VOTE FOR?
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 09:49 AM
Response to Reply #26
33. I voted for Kerry. Doh.
If you insist on misinterpreting me when you don't ignore me, I guess that is your prerogative.

And, as I have said elsewhere, you can declare victory as many times as you want. But the movement would be better served if you made fewer bad arguments and focused more on the good ones. I have no problem with your arguing for fraud in 2004. I have big problems with your arguing badly for fraud in 2004. And you refuse to face the problems. Maybe when I am gone.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 11:31 AM
Response to Reply #33
34. I have sliced and diced the numbers every way from Sunday.
Edited on Fri Jun-24-05 12:15 PM by TruthIsAll
You say, I have argued badly for fraud. No, you have argued badly for NO FRAUD.

No one, you included, has refuted the correctness of my input data or the calculations which use them. The data is publicly available. The calculations are presented for anyone to duplicate.

THE NUMBERS ARE NO LONGER SILENTLY SCREAMING.
THEY ARE SCREAMING LOUD AND CLEAR.

You voted for Kerry?
You could have fooled me.

Where is the outrage?
Where is the analysis?

I challenge you to rebut any of my 100+ threads, including this one, with more than just hypothetical meanderings.

Do the work. I already did. You have 100+ permutations and combinations of exit poll analyses to tear apart. Saying that I argue badly for fraud is intellectual fraud on your part. That's a copout.

Let's face it. You are defying basic logic. It's rBr or its NEP.
You would like to have BOTH. But you can't. One disproves the other.

The conundrum you are facing cannot be undone by just saying that I argue "badly". You are a victim of your own intransigence. You appear to have a very closed mind.

Right now, I can think of just two instances where Duers have found glitches in my calculations. I acknowledged and incorporated both of them. In neither case did they have they have a material impact on the result, but of course I fixed them anyway. As a quantitative engineer/analyst, that is what I have always done and will do.

One change came from you regarding the optimization model. In the other, a DUer found a slight input error in the Excel binomial distribution probability function. The odds went from 1 in 19 trillion to 1 in 13.5 trillion that Bush would exceed the MoE in 16 of 51 states.

The preponderance of evidence says that Bush lost both the electoral AND popular vote. Until you can undue the overwhelming physical and circumstantial mathematical evidence, I suggest that your arguments no longer have any "weight", just like the 43-37 How Voted 2000 weight and all other Final NEP "weights". They are nothing but pure contrivances which have been incorporated to match a bogus vote count.

The Exit Poll Timeline is like OJ's blood trail. OJ got off because the jury was stacked in his favor. So far, Bush has gotten off because the jury (NEP/MSM) has the evidence - and they won't reveal it.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 02:14 PM
Response to Reply #34
38. Where is the outrage?
Presently it is directed at your sloppy analysis. That is the nub of the problem between us right now.

But that isn't to imply that all your analysis is sloppy.

It is simply untrue that I have argued for no fraud, badly or otherwise. In words of one syllable: You made that up. I have argued against certain specific bad arguments for fraud. I think they hurt the cause.

Your inability to grasp my arguments, much less rebut them, is discouraging, but does not evince intellectual fraud on my part or on yours. It is "just one of those crazy things" (gossamer wings not included).
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 02:39 PM
Response to Reply #38
39. You keep calling it sloppy, but you cannot specifically refute a thing.
No, I cannot grasp your arguments, because they are based on faith, not numbers.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 03:18 PM
Response to Reply #39
40. what is this "based on faith" business, anyway?
"People misreport past votes." That is based on evidence, not faith, evidence that has been presented repeatedly.

Tell me if I am getting this wrong. I will try it one more time.

You keep arguing that the 6 point Bush/Gore gap in the weighted 2004 exit poll (43/37%) is mathematically impossible, and therefore we know that the weighted results are wrong, and this proves that Kerry actually got more votes.

But in the 2002 National Election Study, pre-election wave, Bush beat Gore by 7 points (unweighted) or 9 points (pre-election post-stratified weight). (The gap was wider -- over 12 points -- among people who eventually reported having voted in 2002, although of course that should be a relatively small group.)

Is the 2002 result mathematically impossible?

In the 2004 NES, pre-election wave, the gap is narrower (although the difference isn't statistically significant): Bush beat Gore by 4 points (unweighted) or 5 points (pre-election post-stratified weight). The gap was again wider -- 9 points -- among people who later reported having voted in the 2004 presidential election.

If someone had had to guess in advance what Bush/Gore gap an accurate exit poll would yield, what do you think would be a fair guess, or range of guesses? (We get to ignore the 9, since it could not have been known in advance.)
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 03:46 PM
Response to Reply #40
43. So what? 43% of 122.3 is still 52.57. I don't care what your poll said.
Edited on Fri Jun-24-05 03:53 PM by TruthIsAll
I'll keep repeating this until it sinks in.

Bush got 50.456 mm votes
1.77 mm died
48.7 mm alive
48.7/122.3 = 39.82%

Final Exit Poll = Bogus
Final NEP does not represent reality.
Q.E.D.

Did 6% of the voters forget who they voted for?
That is faith-based reasoning.
It is also irrelevant.

Was the Final Poll manipulated to match the vote?
Of course it was. It always is.
Even when that vote is corrupted.

Were the 43/37 weightings IMPOSSIBLE?
Of course they are.
You agree.

Does this result contradict rBr?
Of course it does.

Do you see why?
Of course you do.

Will you admit it?
Of course you won't.

Are you wasting my time?
Of course not.
I enjoy pointing out the facts.

And I will continue to do so from now until you give up the ghost.


Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 04:19 PM
Response to Reply #43
45. if you don't care about polls, then you have no argument
Before you can use recalled vote as a measure, you should conduct some basic QA to determine whether the measure is biased, and if so, how biased it might be.

I press you to estimate the degree of bias in your measure, and you come back with "I don't care what your poll said." (Of course it isn't "my poll," but hey, whatever.)

Assuming that a measure is unbiased because you really, really want it to be -- well, hey, it's a choice.

Calling me a faith-based naysayer -- also a choice.

Accusing people of ad hominems -- also a choice. Sort of an ironic one, I would say.
Printer Friendly | Permalink |  | Top
 
tommcintyre Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 04:44 PM
Response to Reply #45
46. Uh... he really didn't say he didn't care about polls, did he?
He said, "I don't care what your poll said". <bolding and underlining mine - just so you have NO excuse for missing it>

So, there you go - once again. :sigh:
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Fri Jun-24-05 04:50 PM
Response to Reply #46
47. Deleted message
Message removed by moderator. Click here to review the message board rules.
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 04:45 AM
Response to Reply #46
52. OK, so maybe you can explain his position
In another thread, he said "Forget about polling."

In this thread, he said (I will trust your quotation) "I don't care what your poll said."

Is there any poll, other than the 2004 exit poll, that he is willing to consider as evidence?

Does he have a rationale for discounting "my" poll?
Printer Friendly | Permalink |  | Top
 
anaxarchos Donating Member (963 posts) Send PM | Profile | Ignore Fri Jun-24-05 05:52 PM
Response to Reply #45
48. Touchy, touchy....
Quote from above (Post #15):

"(1) TIA makes a post (often in a new thread) with the gist, "Evil naysayers! come bow to the power of my truth, or capitulate!" (I guess I should have put that in caps.)

(2) Someone cheers the power of TIA's truth.

(3) Someone else points out why TIA is actually wrong.

(4) "Someone" (or TIA himself) accuses "Someone else" of evading, or cheating, or "hectoring," or "obfuscating," or being an objective ally of the Bush administration.

This is tedious, yes. Hectoring, quite possibly. But not on my part, I think."

On your part too, I think.

"Ad hominem" is not choice...
Is not accusation...
Is fact...

BTW, I don't mind Ads. I prefer them after the show has started, though.... not before.

You don't mind them either, methinks...


Printer Friendly | Permalink |  | Top
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 04:16 AM
Response to Reply #45
50. Do you know how overwhelmingly the odds are stacked against?
Edited on Sat Jun-25-05 04:18 AM by LightningFlash
Let's have TruthIsAll or an expert mathmetician compute the odds.

Compute all the odds for over 40% of the population, no less, represented by close to 70,000 people MISREPORTING who they voted for in the past election.

Compute those odds right now. Tell me what the figures come out to be, on the one hand....

And on the other hand, tell me how those figures are possible would you please do that? Instead of generalizing....

Go ahead. I imagine we'll see some very lengthy numbers here again. When the exit poll in Florida has been proven right, and Liddle (The one and only Febble) agrees with that analysis too which in fact shows circumstantial fraud proven by corroborated evidence.
Printer Friendly | Permalink |  | Top
 
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 04:49 AM
Response to Reply #50
53. it is not a mathematical question
One can't compute the "odds" of x out of y people misreporting their vote, even notionally, unless one can estimate the underlying probability that any one of them will misreport the vote.

I don't think Febble has said that the exit poll in Florida has been proven right, but if she has, I am happy to hear her out. Every argument is different. I don't decide my opinions on them based solely on whether they are "pro-fraud" or "anti-fraud." I hope you don't either.
Printer Friendly | Permalink |  | Top
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 05:01 AM
Response to Reply #53
54. Actually, one can do exactly that.
Using state by state confirmed polls and census data it is possible to do precisely that. And that is what TruthIsAll I imagine will demonstrate. Hint for recap: The odds are outrageously not in favor of the individuals misreporting their past votes across gender line.
Printer Friendly | Permalink |  | Top
 
Aussie_expat Donating Member (124 posts) Send PM | Profile | Ignore Thu Jun-23-05 09:40 AM
Response to Original message
3. Self deleted
Edited on Thu Jun-23-05 09:42 AM by Aussie_expat
Printer Friendly | Permalink |  | Top
 
Time for change Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 10:41 AM
Response to Original message
6. Does the 43-37 figure apply to the "adjusted" polls?
If so, I don't think that we can take it very seriously anyhow, even if we knew that everyone answered that question accurately.

My guess is that the the 43-37 figure applies to the "adjusted" numbers, and that that's one reason why they are mathematically impossible.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 11:00 AM
Response to Reply #6
7. Yes, you are right. Mathematically impossible.
Edited on Thu Jun-23-05 11:15 AM by TruthIsAll
The 43/37 applies to the FINAL 13660 National Exit Poll.
Impossible.

But if we change it to a possible 39.82/40.25 or a possible 39/39, 39/38, 39/37, 39/36 Kerry wins every time.

Here are 120 scenarios of voter turnout. Each scenario assumes that 100% of Bush 2000 voters turned out. Gore voter turnout ranges from 100% DOWN to 88.6%.

So these 120 scenarios are biased in favor of Bush, based on assumed voter turnout relative to Gore.

Yet....Kerry wins ALL 120 scenarios.

Hard to believe?

BELIEVE.

http://www.democraticunderground.com/discuss/duboard.ph...
Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Thu Jun-23-05 12:23 PM
Response to Original message
12. TruthIsAll, Possibly a 3)...
But I'd like to clarify something first. In the other thread it was stated that the 2000 question was based on ~4000 responses. I couldn't find the source for this but was taking it as reliable because you didn't dispute it.

Can you verify that the 2000 vote numbers are based on 4000 responses? If so, were only 4000 asked this question or did only 4000 reply with the other 9000+ choosing not to answer it?

Thanks.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 02:37 PM
Response to Reply #12
16. It was 3168 respondents. Here's a link.
Edited on Thu Jun-23-05 02:45 PM by TruthIsAll
As to why only 3168 responded, I seem to recall reading that the full set of questionnaire forms were not available in all the precincts.

http://www.exitpollz.org/mitof4zone/US2004G_3970_PRES04...
Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Thu Jun-23-05 05:26 PM
Response to Reply #16
21. 3) No contradiction
How do we know the 3168 sample had the same distribution of Bush voters as the 13660? We don't.

If, for whatever reason, the 3168 sample had a higher Bush voter bias, this is exactly the results we should expect.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 06:18 PM
Response to Reply #21
22. Makes no diff. 43% is impossible. MoE = 1/sqrt(3168) = 1.78%
You continue to miss the point.

And if 43/37 is what you would expect, even if impossible, tell us how it is consistent with rBr.

You want the IMPOSSIBLE 43/37?
Fine, but you cannot at the same time cling to the IMPLAUSIBLE rBr.

THEY ARE MUTUALLY EXCLUSIVE.

DO YOU AGREE?
Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Thu Jun-23-05 07:55 PM
Response to Reply #22
23. Disagree...
It's entirely possible with 2 different sets of sample data.

Suppose for a moment the 13660 was skewed toward Kerry. rBr, skewed precinct selection, interviewer bias, whatever... it doesn't matter for this exercise. But don't you agree it is plausible?

Now suppose the 3168 was skewed toward Bush (entirely possible since it is a subset of the 13660). Again, at this point don't worry about why, but can we agree it COULD happen?

What affect would a Kerry skew on the total vote and a Bush skew on the last election question have on the calculated percentages for the 2000 election question when the poll was weighted with tallied vote count data?
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Fri Jun-24-05 03:13 AM
Response to Reply #23
27. Deleted message
Message removed by moderator. 
[link:www.democraticunderground.com/forums/rules.html|Click
here] to review the message board rules.
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 03:56 AM
Response to Reply #27
28. Astute observation. Sampling bias could not overcome the gap.
Only systematic fraud such as this has that ability to do so....




This only proves it.
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Fri Jun-24-05 06:50 AM
Response to Reply #27
30. Deleted message
Message removed by moderator. Click here to review the message board rules.
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 07:17 AM
Response to Reply #30
31. Go ahead, set it up. Verify your theory.
Anyone can always say anything COULD HAVE happened.
That is no theory.
That is conjecture.
I deal in reality.

You are reduced to saying that it could snow in Caracas today.
Well, yes, maybe it will, just like it did during the Ice Age.

In any case, you have NOT responded to even one of the 120 scenarios.
Why not?

They incorporate all pro-Bush scenarios of voter turnout for various percentages of Keerry share of NEW voters - from the real exit poll timeline (11027-13047 respondents) to the fake (13660).

I gave you every possible combination of variables to work with.
I even stacked them in your favor.

And you still come up short.

Go ahead.
Fire up your bogus, faith-based scenario.
I can't wait to see it.
Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Fri Jun-24-05 12:30 PM
Response to Reply #31
35. Hmmm... deleted message.
Edited on Fri Jun-24-05 12:32 PM by WI Independent
In review...

You post:
"Good question.
Even if someone fed it to you.

Thought you were going to derail my logic?

When will you learn?
Not ONE naysayer has ever been able to it.


Many have tried.
You are just the latest.

After you are done reading this, what will be your next
fruitless attempt to turn common sense and SOUND logic on its
head?
"

Your post remains.

I post that "your condescending attitude seems to be intact" and offer to do my own calculations when I have the time.

My post is deleted.

You come back calling whatever I might do "bogus" and "faith based" without even seeing it.

I'm sure your post will remain, though I think this one is likely short-lived.


In conclusion, it appears you are correct in saying I can't dispute your arguments... at least not in this environment.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 12:47 PM
Response to Reply #35
36. That's a copout . Just show us your spreadsheet.
Edited on Fri Jun-24-05 12:48 PM by TruthIsAll
I had nothing to do with that deletion. I look forward to your excel.

I NEVER LIKE TO SEE ANY POSTS DELETED. NOT MINE, NOT ANYONE. I WOULD RATHER THE OFFENDING POSTS JUST BE NOTED IN RED.

So let's move on. Don't quit on that note. Show us your analysis.

I will try not to appear condescending. If I have been, it's due to frustration of seeing legitimate analytic discourse overcome by naysayer fog.

Printer Friendly | Permalink |  | Top
 
WI Independent Donating Member (156 posts) Send PM | Profile | Ignore Fri Jun-24-05 01:14 PM
Response to Reply #36
37. Fair enough...
Edited on Fri Jun-24-05 01:16 PM by WI Independent
Now I feel bad for alerting your post above my deleted one right after I made my last reply. :( Hopefully the Admin ignores me.

EDIT: Ooops, it's gone now... my apologies TIA. :(

Sometimes I forget as a non-Democrat (don't get excited... non-Republican, non-whatever as well), this is much less personal to me than it is most on here. I will try to stay more aware of that in the future. I am not out to "get" anyone, merely trying to engage in discussion.

As I said... I'm not sure when I'll have the time but I really want to look at the numbers more closely. Lunch is over... back to work for me. :)

Peace...
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 03:22 PM
Response to Reply #37
41. I admit, I can be gruff, I can err, but my credibility is 100%
And I will never, ever, succumb to self-delusion or denial.If
I believed for ONE MINUTE  that Bush won, you would never know
me.
I would not be posting  at DU day after day. 

All I ask is that if one disagrees with my analysis, that it
be pointed out specifically as to where and why. I can deal
with legitimate criticism, but I have seen quite the opposite
from the naysays.  I am willing to make adjustments to any of
my posts, provided that there is a legitimate error in either
the data OR the analysis. In fact, if you look back at my
posts, as soon as I spot an error, I have corrected it
immediately. That's why the naysays can't spot errors - they
are fixed before they know it. So instead, they focus on ad
hominems in their attempts to cast doubt on my analysis.
Unfortunately for them, since they never apply the effort to
analyze the data to the extent that I do, they are always
caught short in the logical argument.

I deal in specifics, not generalities; in facts, not talking
points; in realities, not hypotheticals. Quite frankly, WI, I
have found naysayers uninterested in arguing the facts, yet
very interested in thrashing my work.

I have NEVER, EVER, FUDGED, TWISTED OR TRIED TO MISLEAD OR
DIVERT.
I present all the data, all the calculations. Just review the
100+ posts I have done since January.

IF I IGNORE A POST, IT'S BASED ON MY EXPERIENCE THAT IT IS
DISINGENUOUS AND MEANT TO DISTRACT AND WEAR ME DOWN, WHEN I
HAVE ALREADY RESPONDED IN A PRIOR POST. THEN THE NAYSAYER
CRIES THAT I  AM REFUSING TO ANSWER THE POST, IN A VAIN
ATTEMPT TO DESTROY MY CREDIBILITY.

I try initially to keep the tone at a moderate level, but if I
feel the argument being made is just an excuse to bait me, my
antenna  spots it very quickly and I lose patience and react
verbally.  I certainly have enough experience in being baited.

If you want to know where I or anybody is coming from, just
check the DU archives. There is a permanent record there which
no one can hide from. 
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Fri Jun-24-05 03:31 PM
Response to Reply #41
42. Deleted message
Message removed by moderator. Click here to review the message board rules.
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 04:02 PM
Response to Reply #42
44. x
.
Printer Friendly | Permalink |  | Top
 
Febble Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 04:00 AM
Response to Reply #41
49. OK, to put the record straight:
Edited on Sat Jun-25-05 04:21 AM by Febble
I referred to TIA on DKos:

http://www.dailykos.com/story/2005/6/22/183230/208

so it is only fair that I comment here.

Here is where I agree with TIA:

I agree that his table showing the "12.22" exit poll responses shows a) Kerry winning and b) proportions of respondents who say they voted for Bush and Gore respectively that match the proportions that actually voted for Bush and Gore in 2000.

One possible interpretation therefore, is that the poll responses accurately reflected both the proportions of votes in 2000 and the proportions of votes in 2004.

I also agree with TIA that his table showing the "1.25" responses shows a) Kerry losing and b) proportions of respondents who say they voted for Bush and Gore that do not match the proportions who actually voted for Bush and Gore in 2000. Moreover, I agree with TIA that not only are the proportions wrong for the 2000 vote in the second table, the proportions are impossible, as it that implies more repeat Bush voters in 2004 than actually voted for Bush in 2000.

One possible interpretation of this, therefore, is that the responses have been reweighted to match the results (we know this was done), but that the fact that this reweighting makes the plausible number of Bush repeat voters implausible (and in fact, impossible) suggests that the vote count used for the reweighting must have been fraudulent.

This is a good argument. It makes mathematical sense. And I agree that it is suggestive that the Gore/Bush proportions in the early table actually match the vote-count Gore/Bush proportions, a point in favour of their veracity. So far so good.

Here is where I diverge from TIA's thinking:

Suppose there is a discrepancy between the count and the poll, as there was. And that this was either due to the fact that Kerry voters had been polled at, say 1.12 times the rate of Bush voters, or that a proportion of Kerry votes had been switched to Bush (I haven't worked out the proportion, but I know TIA has).

When the precinct results start to come in, the E-M computer program will start to discover this, and reweight the projections in line with the precinct results. I do not know how this is done, only that it is done, and I know this from the E-M FAQ:

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


How are projections made?
Projections are based on models that use votes from three (3) different sources -- exit poll interviews with voters, vote returns as reported by election officials from the sample precincts, and tabulations of votes by county. The models make estimates from all these vote reports.


My guess is that the way it is done is by identifying particularly categories of responses (from a particular demographic group, say) that seem to be most divergent, and adjusting those. I imagine it works rather like your optimizer, except that the constraints on the output start being very loose and only become tighter as the results come in.

And we know that when the final adjustment had been made, the projection made a nonsense of the Gore/Bush responses.

One reason for this nonsense, could, I agree, be fraud. However, I see two alternative explanations that I find plausible, though I respect your right to disagree.

One is that no-one knows whether the weightings were correctly applied - my guess is that they would be optimized to constraints more binding (like gender) than past vote, as past vote is a notoriously unreliable measure. However, there are almost certainly multiple solutions to the possible weights that could be applied to match the poll data to the count data (and I agree - who could not? - that they were matched: they were designed to be matched) and some may give a more veridical match to the Gore/Bush proportions. So the final Gore/Bush proportions may simply be wrong, even though the estimate of the vote count now matches the vote count. Weighting solutions may exist that do a better job of approximating the actual Gore/Bush proportion.

But secondly, I do not believe the Gore/Bush raw responses are necessarily accurate. I find it plausible that the initial proportions of Gore/Bush respondents only coincidentally matched reality. I am not saying this is so, just that it could be so. In other words it is possible that the final table tells you something real about what people who voted for Bush in 2004 wanted to think about they way that they had voted in 2004. And that some Bush voters in 2004 wanted to think they had voted for Bush in 2000, whether they had in fact voted for him, or whether in fact they had voted at all. We know, from good research, that people do this.

However, I do not think this is necessarily the case. I think it may simply be an artefact of the way the weighting was done.

But it means that although I follow your mathematical reasoning, I cannot agree that Gore/Bush proportions in the final table are incontrovertible proof of fraud, particularly in the light of evidence that bias was greater where random sampling protocol was most likely to be compromised, for example, where interviewing rate - the rate at which voters are selected for interview - was low.

And I think to assert that it is incontrovertible proof is misleading. It is contingent on a notoriously unreliable measure of past voting behaviour from a minority subsample of the participants in the poll, and moreover, the final Bush/Gore proportions diverge from what is possible in exactly the way that one would expect - that people like to report have previously voting for the person they are currently voting for. I think it is known as the "consistency bias".

However, these are behavioural arguments, not mathematical. I do not dispute your math.

Please join the debate with me on DKos if you would like. I won't respond on DU again, for reasons I gave in my last post.

(edited for typo)
Printer Friendly | Permalink |  | Top
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 04:22 AM
Response to Reply #49
51. Excellent math. And it gives us true reasoning to the argument...
The glitches in the final weighting could have been the result of computer malfunction or other systematic bias, because we don't have access to the voters news service computers.

On the one hand, since we can't review this evidence it makes it suspect. On the other hand, the very fact Mitofsky refuses to show even the simplest data without revealing privacy makes it as suspect as Diebold software. Which raise the suspicions of systematic fraud in at least 6 states....
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 07:30 PM
Response to Reply #49
55. " I do not dispute your math."
The mathematical analysis does not to offer "incontrovertible proof of fraud." If we had incontrovertible proof, we would be discussing it on DU or Daily KOS, we'd be front page everywhere (except the USA, of course).

The argument here is that we need an investigation, a serious one, looking at fraud specifically from all angles, in part, because of the arguments TIA presents here.

The various forms of fraud, which we agree upon, plus indisputable math is a sufficient criterion to trigger such an investigation.
Printer Friendly | Permalink |  | Top
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 09:05 PM
Response to Reply #55
56. And also find a fully reproduceable pattern.
All the patterns of "incorrect" polling procedures do not provide any solid fully reproduceable pattern because they did not happen--Not because they were a stroke of luck.

But patterns of incorrect vote counting and fraud did happen, and a reproduceable pattern can be found.....If a serious investigation is submitted.



And once that pattern is fully realized, the smoking official gun and lying BOE members can be caught.

Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Jun-25-05 10:17 PM
Response to Reply #56
57. Cobb: 34%; Kerry 34%; Bush 30% -- HAMILTON COUNTY
Wow, now that's a vote tally that inspires confidence. Thanks for sharing this here and in other places. It is most useful. I guess the good folks of Hamilton are uniquely progressive in selection Cobb over Bush at this point of the tally. I'm impressed. Maybe I'll locate my green solar power business there. Quite a reception!

"lying BOE members can be caught. That's right. All the liars will be caught eventually. What a great day for America!

Thanks LighteningFlash!!!!!!!!!!!!!!!!!!!!!!
Printer Friendly | Permalink |  | Top
 
LightningFlash Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 01:12 AM
Response to Reply #57
59. Just doing my little bid of duty to democracy. For a friend. n/t
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 03:13 PM
Response to Reply #49
60. Febble, my response...
Edited on Sun Jun-26-05 03:22 PM by TruthIsAll
YOU:
I referred to TIA on DKos:

http://www.dailykos.com/story/2005/6/22/183230/208

so it is only fair that I comment here.

Here is where I agree with TIA:

I agree that his table showing the "12.22" exit poll responses shows a) Kerry winning and b) proportions of respondents who say they voted for Bush and Gore respectively that match the proportions that actually voted for Bush and Gore in 2000.

One possible interpretation therefore, is that the poll responses accurately reflected both the proportions of votes in 2000 and the proportions of votes in 2004.

I also agree with TIA that his table showing the "1.25" responses shows a) Kerry losing and b) proportions of respondents who say they voted for Bush and Gore that do not match the proportions who actually voted for Bush and Gore in 2000. Moreover, I agree with TIA that not only are the proportions wrong for the 2000 vote in the second table, the proportions are impossible, as it that implies more repeat Bush voters in 2004 than actually voted for Bush in 2000.

One possible interpretation of this, therefore, is that the responses have been reweighted to match the results (we know this was done), but that the fact that this reweighting makes the plausible number of Bush repeat voters implausible (and in fact, impossible) suggests that the vote count used for the reweighting must have been fraudulent.

This is a good argument. It makes mathematical sense. And I agree that it is suggestive that the Gore/Bush proportions in the early table actually match the vote-count Gore/Bush proportions, a point in favour of their veracity. So far so good.

ME:
You agree with the math. Thats an excellent start. Therefore, it logically follows, and I assume you agree, that the Final Exit Poll is no longer viable on its face, since the weightings are impossible. Would you also agree that anyone who reads the poll and does not bother to check the 43%/37% split for feasibility, much less plausibility, would be misled into thinking that the exit poll results are legit?
Do you also agree that the Final 13660 NEP, which has been proven as fiction, should not be presented by the media in its current form, since it misrepresents the reality which you have just stipulated to?

As I see it, your response from this point on rests on two very suspect hypotheticals.
1) Gore voters lied or forgot who they voted for in 2000 when they said they voted for Bush
2) Kerry voters were more apt to respond to the exit pollsters, by a 1.12/1 ratio over Bush voters.

Ok, lets continue.

You say:
Here is where I diverge from TIA's thinking:

Suppose there is a discrepancy between the count and the poll, as there was. And that this was either due to the fact that Kerry voters had been polled at, say 1.12 times the rate of Bush voters, or that a proportion of Kerry votes had been switched to Bush (I haven't worked out the proportion, but I know TIA has).
I say:
First of all, a correction. The MINIMUM response ratio is 1.155/1. The optimizer has shown, using the WPE and aggregate response data supplied by Mitofsky, that THERE IS NO FEASIBLE SOLUTION FOR alpha <1.155 which will satisfy the constraints.

You say:
When the precinct results start to come in, the E-M computer program will start to discover this, and reweight the projections in line with the precinct results. I do not know how this is done, only that it is done, and I know this from the E-M FAQ:

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

How are projections made?
Projections are based on models that use votes from three (3) different sources -- exit poll interviews with voters, vote returns as reported by election officials from the sample precincts, and tabulations of votes by county. The models make estimates from all these vote reports.


My guess is that the way it is done is by identifying particularly categories of responses (from a particular demographic group, say) that seem to be most divergent, and adjusting those. I imagine it works rather like your optimizer, except that the constraints on the output start being very loose and only become tighter as the results come in.

I say:
Yes, you are guessing. You DO NOT know how the projections are done. And to suggest that the projections work like the Exit Poll Optimizer is 100% incorrect.

The Optimizer does not project anything. It just tells us whether or not a particular result is feasible, given a set of constraints. In the case of the Optimizer, to repeat, the constraints ARE NOT MINE. They were supplied by Mitofsky. And they show that his 1.12 alpha hypothesis is IMPOSSIBLE , because it contradicts his precinct WPEs and 53% aggregate response rate.

You say:
And we know that when the final adjustment had been made, the projection made a nonsense of the Gore/Bush responses.

I say:
I agree.

You say:
One reason for this nonsense, could, I agree, be fraud. However, I see two alternative explanations that I find plausible, though I respect your right to disagree.

One is that no-one knows whether the weightings were correctly applied - my guess is that they would be optimized to constraints more binding (like gender) than past vote, as past vote is a notoriously unreliable measure. However, there are almost certainly multiple solutions to the possible weights that could be applied to match the poll data to the count data (and I agree - who could not? - that they were matched: they were designed to be matched) and some may give a more veridical match to the Gore/Bush proportions. So the final Gore/Bush proportions may simply be wrong, even though the estimate of the vote count now matches the vote count. Weighting solutions may exist that do a better job of approximating the actual Gore/Bush proportion.

I say:
Your first reason (that it was fraud) is the MOST PLAUSIBLE by a mile and has been proven beyond any REASONABLE doubt. Not just by analysis of the Exit Polls, but the Exit Polls in conjunction with DOCUMENTED VOTER SUPPRESSION, UNVERIFIABLE TOUCH SCREENS, UNVERIFABLE OPTICAL SCANNERS AND UNVERIFIABLE CENTRAL TABULATORS.

But I agree, lets see those weighting solutions. I have shown that in the three exit poll timelines (8349 to 11027 to 13047 respondents) that Kerry won each and every one of 10 demographic calculations. Thats a total of 30 calculations, done exactly the same we have already shown in the How Voted in 2000 demographic.

The fact is, the How Voted in 2000 demographic statistics are the ONLY ones which can be independently verified. We have shown, and you have agreed, that the 2004 vote (122.3mm) and the 2000 votes for Gore (50.999mm) and Bush (50.456mm) are incontrovertible and have a ZERO MoE.

The fact is that EACH and EVERY ONE one of the other Exit poll demographics was ALSO matched to the vote.

In some cases the weight was not changed (54% Female/46% Male), but Kerrys percentage was, from 54% of the female vote (at the 13047 timeline) to 51% in the Final 13660.

In the case of Party ID, the weights were changed from 38% Dem/35% Rep/ 27% Independent in the 13047 timeline to 37%/37%/26% in the Final 13660, but in addition the percentages of the votes were ALSO changed in favor of Bush, because just changing the weights was not enough to match the vote by itself.

You say:
But secondly, I do not believe the Gore/Bush raw responses are necessarily accurate. I find it plausible that the initial proportions of Gore/Bush respondents only coincidentally matched reality. I am not saying this is so, just that it could be so. In other words it is possible that the final table tells you something real about what people who voted for Bush in 2004 wanted to think about they way that they had voted in 2004. And that some Bush voters in 2004 wanted to think they had voted for Bush in 2000, whether they had in fact voted for him, or whether in fact they had voted at all. We know, from good research, that people do this.
However, I do not think this is necessarily the case. I think it may simply be an artefact of the way the weighting was done.


I say:
You always couch your arguments with I am not saying this is so, just that it could be so.

Well, yes, it could snow in Caracas tomorrow.

What is the rationale for assuming that Gore voters would forget who they voted for?
Isnt it more PLAUSIBLE to assume that since they knew the 2000 election was stolen from Gore in Florida (with help from SCOTUS) that they would be HIGHLY MOTIVATED to exact justice by coming out in groves for Kerry? And do you really suspect that Gore voters fell in love with Bush, based on his (cough) performance in office?


You say:
But it means that although I follow your mathematical reasoning, I cannot agree that Gore/Bush proportions in the final table are incontrovertible proof of fraud, particularly in the light of evidence that bias was greater where random sampling protocol was most likely to be compromised, for example, where interviewing rate - the rate at which voters are selected for interview - was low.

And I think to assert that it is incontrovertible proof is misleading. It is contingent on a notoriously unreliable measure of past voting behavior from a minority subsample of the participants in the poll, and moreover, the final Bush/Gore proportions diverge from what is possible in exactly the way that one would expect - that people like to report have previously voting for the person they are currently voting for. I think it is known as the "consistency bias".

However, these are behavioural arguments, not mathematical. I do not dispute your math.

I say:
Incontrovertible proof. What is that? How about proof beyond a REASONABLE doubt?
You have not provided a modicum of reasonable doubt.

You say:
Please join the debate with me on DKos if you would like. I won't respond on DU again, for reasons I gave in my last post.

I say:
That is not necessary. First of all, DU is where I spend my time. Secondly, DKos is too complicated to use. Thirdly, I do not wish to be distracted in endless, fruitless argument.

I have stated the case. You have stated yours.

I only ask that you post this thread on DKos and let others form their own opinion.



Printer Friendly | Permalink |  | Top
 
Febble Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 05:30 PM
Response to Reply #60
62. Posted on Dkos
Here:

http://www.dailykos.com/comments/2005/6/22/183230/208/2...

together with a brief response:

I am happy to agree with TIA that his proof has not been, and should not be described as "incontrovertible". Sadly, no proof of anything in the exit poll debate is likely to be incontrovertible. I remain unconvinced that his argument takes us beyond "reasonable doubt".

The essential difference between us (and probably between "fraudsters" and "naysayers") probably boils down to those who find it plausible that:

1) Gore voters lied or forgot who they voted for in 2000 when they said they voted for Bush
2) Kerry voters were more apt to respond to the exit pollsters, by a 1.12/1 ratio over Bush voters.

and those who do not. I find it plausible, but then I am a behavioural scientist.


And an extra, for DU:

None of the above means that I believe your electoral system is fair, secure or uncorrupted. I think it is none of these things. Whether "Kerry won" or not, the system needs fixing.

I wish you all well.

(and can I leave you with one of the most inspiring diaries I ever read on DKos, just in case you think we are all "naysayers":

http://www.dailykos.com/storyonly/2004/12/15/9734/4841

Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 05:48 PM
Response to Reply #62
63. Febble, I wish you well. You have provided the reasonable doubt.
Thank you. Of all the many visitors to DU Elections, you are the only one who will actually engage in a debate and follow through to a logical conclusion.

We're at the point where you have accepted TIA's mathematical calculations (perhaps even aided the latter versions of his work through your 'stimulus,' his work is better than ever). You say it's not proof beyond any doubt to the contrary. Well, we agree. However, this statement is what is needed to justify a full investigation.

Essentially, you have agreed that fraud is a logical, although not exclusive, interpretation of TIA's analysis. On that we all agree. You seem to offer a 'behavioral' explanation: either rBr or amnesia on the part of Gore voters in responding to their preference. rBr has been addressed thoroughly and I believe fails the acid test. Gore voter amnesia, well, consider this. Gore voters would be a major subset, a majority, of Kerry voters and responders. Part of the argument has centered around exuberant Kerry responders. So bear with me here, if I'm an exuberant Kerry responder, I'm extremely likely to be aware that I was an Gore voter (maybe very aware). Thus I'd not only be an exuberant Kerry responder, I'd also be a exuberant Gore recollector. Given the co-occurrence of Kerry voter 2004/Gore voter 2000, and the imputed exuberance of Kerry voters, there's no reason to think that the behavioral argument on former Gore voter amnesia/reluctance holds any water.

Three choices: 1) fraud; 2) rBr; 3) Gore voter amnesia/reluctance.

You're intellectually honest. You know that the conclusion is 1) fraud, not as proof beyond any doubt, but as a STRONG INDICATOR THAT THERE WAS SOMETHING VERY WRONG WITH 2004 AND THAT THERE NEEDS TO BE A VIGOROUS INVESTIGATION.

Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 07:27 PM
Response to Reply #62
65. Thanks, Febble, for your gracious response...
Edited on Sun Jun-26-05 07:29 PM by TruthIsAll
Thanks for posting this on DKos. You have let others beside DUers form their own opinions. That is commendable. In fact, I could ask for nothing more.

We differ on what is plausible, indeed on what is possible. But I congratulate you on your near-perfect presentations and use of the language.

And, of course, you never said that fraud did not occur. You have helped extend the debate to this point. I will continue to post on DU when I believe there is something to add to what I have previously done.

So far, I have not seen one argument which has swayed me in the slightest from believing that fraud occurred in many shapes and forms. At some point, and we are getting there, the truth and history of this election will become common knowledge.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 05:21 PM
Response to Reply #49
61. Febble, one more thing...
Edited on Sun Jun-26-05 05:29 PM by TruthIsAll
This is what it would take for Bush to TIE Kerry.

Bush would need 100% of his 2000 voters to turnout while only
78.4% of Gore voters turn out. For any greater Gore turnout,
Bush would lose.

Of course that means there would have to be 25.63% of NEW
voters as a percent of the total 122.3mm.

And we know Kerry won the NEW voters. 
All the timelines say so, even the bogus final 13660 (54%).

I use the vote percentages from the 13047 timeline because
they make more sense:

	MIX	Bush	Kerry	Nader	Bush	Kerry	Nader
No	25.63%	41%	57%	2%	10.5%	14.6%	0.5%
Gore	31.55%	8%	91%	1%	2.5%	28.7%	0.3%
Bush	39.82%	90%	10%	0%	35.8%	4.0%	0.0%
Other	3.00%	13%	65%	16%	0.4%	2.0%	0.5%
	100%				49.26%	49.25%	1.31%
	total				60.25	60.23	1.60




But I know you would prefer to see the calculation done for
the 13660 Final which was matched to the Bush vote.

S lets look at the breakeven for a Kerry 54% share of NEW
voters:

	MIX	Bush	Kerry	Nader	Bush	Kerry	Nader
No	23.18%	45%	54%	2%	10.4%	12.5%	0.5%
Gore	34.00%	8%	91%	1%	2.7%	30.9%	0.3%
Bush	39.82%	90%	10%	0%	35.8%	4.0%	0.0%
Other	3.00%	13%	65%	16%	0.4%	2.0%	0.5%
	100%				49.38%	49.39%	1.28%
	total				60.39	60.40	1.57

Bush would need a maximum of 34% for Gore voters to TIE.
For any larger turnout of Gore voters, Bush loses.
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 08:30 AM
Response to Reply #30
32. The party line "emerges" -- quickly too.
Printer Friendly | Permalink |  | Top
 
mgr Donating Member (616 posts) Send PM | Profile | Ignore Mon Jun-27-05 10:22 AM
Response to Reply #22
66. The two are not mutually exclusive
The presumption that any pollster makes is that the population that responds, and the non-respondants have the same make up. There is no inherent justification for this, and Rbr, suggests that the two may be disparate.

What the 43/37 split in Bush/Gore votes may reflect sampling error in that the population subsampled within the question asked may vary from the overall sampled population, and not reflect the non response population at all.

I have already stated that I am quite comfortable with the 43/37 being just beyond the MoE for the reason above. The measure is subjective in that it only gives a sense of movement towards or away from candidates, and may measure to some degree the incumbent effect. In that sense, one can anticipate that non participants in the previous election may express voting preference they did not register as a vote.

The error in your thinking is that you fail to fully appreciate that reweighting for the vote is what extrapolates to what the non response population may have been. You cannot formulate the hypothesis (Rbr)unless there is some data to back it up. NEP did not get this out of thin air.

Mike
Printer Friendly | Permalink |  | Top
 
mgr Donating Member (616 posts) Send PM | Profile | Ignore Thu Jun-23-05 04:17 PM
Response to Reply #12
20. That was a rough approximation.
What it is, is that if your review the NEP national election questionaire, there are four separate ones. Since separate questions are included in the final weighting, one would presume that a quarter of the ~13,000 would have answered each question. I do not know what the response or refusal pattern is.

I've been in field today, and was going to look closer at the questionaire, because I think some questions may occur in each, but others are only present in a quarter.

Mike
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Jun-23-05 10:25 PM
Response to Original message
24. KICK and Final Grades
:kick:

Final Grades:

---Quality of Post: A+


Comment: Outstanding post, test narrative shows ongoing improvement, logical reasoning using previous thread(s) superb.

---Quality of Debate: F


Comment: Nobody seems to be challenging the logic of the post and many seem tepid about actually engaging in real debate. Characteristic of CannonFire's definition of a liberal, "a liberal being defined as someone who finds his own beliefs endlessly questionable." Summer school required to advance.
Printer Friendly | Permalink |  | Top
 
kster Donating Member (1000+ posts) Send PM | Profile | Ignore Fri Jun-24-05 01:57 AM
Response to Reply #24
25. kick.nt
Printer Friendly | Permalink |  | Top
 
kster Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 12:46 AM
Response to Reply #25
58. double kick..nt
Printer Friendly | Permalink |  | Top
 
autorank Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Jun-26-05 06:21 PM
Response to Reply #24
64. Modified grades.
Edited on Sun Jun-26-05 06:24 PM by autorank
Febble is not associated with the "F". She actually helped the debate in this thread. 6/26/05
Printer Friendly | Permalink |  | Top
 
tommcintyre Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-25-05 07:59 PM
Response to Original message
67. kick - In tribute to his tremendous contributions - WHY??? :( n/t
Printer Friendly | Permalink |  | Top
 
bleever Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-25-05 10:36 PM
Response to Original message
68. Kicking for truth, justice, and TIA's invaluable work.
Printer Friendly | Permalink |  | Top
 
DU AdBot (1000+ posts) Click to send private message to this author Click to view 
this author's profile Click to add 
this author to your buddy list Click to add 
this author to your Ignore list Wed Aug 23rd 2017, 08:31 PM
Response to Original message
Advertisements [?]
 Top

Home » Discuss » Topic Forums » Election Reform Donate to DU

Powered by DCForum+ Version 1.1 Copyright 1997-2002 DCScripts.com
Software has been extensively modified by the DU administrators


Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

Home  |  Discussion Forums  |  Journals |  Store  |  Donate

About DU  |  Contact Us  |  Privacy Policy

Got a message for Democratic Underground? Click here to send us a message.

© 2001 - 2011 Democratic Underground, LLC