Febble Response to our replies to OTOH's Paper

[davidgmills]

David, the thing is full of numbers. The writing is to tell you the results of the analysis of the numbers. Come on. What he has shown is that the states that, according to TIA had results with large "surprises" (i.e. big difference between pre-election polls and vote count) were NOT the same states that had large exit poll "surprises" (big differences between exit polls and vote count).

This is a problem for any hypothesis that attributes the "surprises" to fraud. If the pre-election surprises were caused by the same factor as the exit poll surprises, you'd expect the two lots of surprises to be positively correlated . In other words if there was fraud in state X you'd expect both the pre-election poll surprise to be large (because of fraud) AND the exit poll surprise to be large (because of fraud). And there was no fraud in state Y, you'd expect the pre-election poll surprise to be small AND the exit polls surprise to be small. Obviously there will be a bit of extra variance (although if TIA is to be believed, it will be very small because of the small MoEs, especially in the exit polls). But there should be a significant POSITIVE correlation. But taking the most generous estimates he could, Lindeman failed to find anything significant apart from the odd NEGATIVE correlation.

You can't just write it off. TIA needs to address the findings, and all the quantative information he requires is accessible from the paper. Otherwise his case falls apart.

It's possible, as Lindeman says, that fraud was uniform. But that isn't what anyone is claiming, least of all TIA.

Correction:

All the data used to address TIA's analyses is accessible, because it is derived from TIA's own spreadsheet. Exit poll data is from the E-M report. Only the E-M pre-election data, as far as I can see, is not given, but it apparently yielded similar results.

Scatterplots, from which values can be approximated directly, are also given. There is no shortage of numbers.

[TruthIsAll]

When will you guys ever learn?
Don't you know by now that you can NEVER catch me short-handed?
That I will always beat your attempts to debunk my work?
And in so doing, I will destroy your straw man arguments.
I guess you're just gluttons for punishment.
Well, OK.
Here we go again.

Yes, Febble, there really is a Clincher.
http://www.progressiveindependent.com/dc/dcboard.php?az=show_topic&forum=120&topic_id=1445

Here's my "surprise" function:
Let's address the pre-election state polls matching the state exits.
Take a look at the table at the bottom of this post.
The average 2-party Kerry pre-election poll (50.37%) matched the
average exit poll (50.51%) to within 0.14%.
Pretty close fit, eh?

Notice the battleground states.
They match more closely than the rest.
Makes sense. Larger samples.

OTOH, it's too bad you didn't get around to printing this.
All you guys ever do is blind us with scatter-shots.
Eyeball the individual state poll comparisons.
You can even compare them to the actuals.
Why don't you guys do a correlation analysis?
Show all those t's and p's.

Here's a link to the original DU thread if you still want to go there:
http://www.democraticunderground.com/discuss/duboard.php?az=show_topic&forum=203&topic_id=330449

The misrepresentations and obfuscations just fall apart.

There are FOUR variables to consider, not just TWO:
Pre-elect state = pre-elect national = post-elect state = post-elect national
THEY ARE ALL IN CONFIRMATION.

OTOH did not put a dent into my analysis.
NO "SURPRISE" FUNCTION THERE.
His analysis did nothing to obscure...THE CLINCHER ARGUMENTS.
He downloaded the Interactive Election Model, but he never discussed:

1) Pre-election National Polls.

2) Sensitivity Analysis debunking the Final NEP.

3) Precinct Exit Poll response optimizer (debunking rBr).

4) State Exit poll response optimizer.

5) He mistated the Ohio pre-election/exit poll confirmation:
The Zogby poll (Kerry 50/Bush 47) EXACTLY matched the exit poll
(Kerry 52/ Bush 48)- after allocating 2/3 of the undecided to Kerry.

6) National Census 3.4 million vote count discrepancy.
What happened to the votes, most of which were Kerry's?
How come OTOH doesn't factor the net 1 million or more discrepancy into his "Surprise" statistics?

7) The Pew Poll.
Once again, OTOH failed to mention the Pew final Registered Voter (RV)
poll in which Kerry was leading by a point (an 8% gain in one month).
This is just another indicator that undecided voters went for Kerry.
All National Exit Poll timelines confirm that 55-65% of the undecided
voted for Kerry, depending on the time period (1,3,30 days).

What is it about the Pew poll, anyway?
OTOH seems obsessed by it.
I used 18 pre-election polls in the Election Model.
But he's got this thing for Pew.
He doesn't like the fact I used the RV poll.
It must have demoralized him when he checked it out.

I had a logical rationale for using RV polls when available:
MASSIVE Democratic voter registration.

OTOH calls it cherry-picking.
Where is it written that I must use LV polls?
I chose polls BEFORE THE FACT (ELECTION)in the Election Model.
OTOH cherry-picks the Pew LV poll AFTER THE FACT.
What a pathetic attempt to rebut my analysis.

8) The numbers for AZ are correct, by the way, in the Interactive Model.

9) Using FEASIBLE NEP weightings and 98% turnout results in a 4.57mm
vote switch from Bush to Kerry, giving him a 6.14mm winning vote margin.
So the 10 million vote switch quoted by OTOH required as per Freeman
is just misleading jargon. And Freeman's 6 mm Kerry margin agrees with mine.

QUERY MAS?

I'll add more stuff to this list as time goes on.

OTOH tried his best. I will give him that.
Too bad you guys have nothing substantial to work with.

The bottom line:
Kerry won the Pre-election state polls and national polls.
Kerry won the Post-election state and national exit polls.
Tangible proof of election fraud abounds.

rBr is as dead as a crabmeat dinner.
A Republican reluctant to speak to pollsters probably voted for Kerry.
And was either ashamed or scared (or both) of saying so.

"False recall"?
Do you know ONE Democrat who forgot Gore was robbed?
Do you know ONE who forgot that he/she has ALWAYS voted Democratic?

Oh, BTW, Febble: remember the DU Game thread?
You both lost that one.
The only thing you won was getting me banned from DU.

Febble, once again I beseech thee:
Respond to the challenge.
Download the model at the bottom of the screen.

Give us just ONE plausible Bush win scenario.
Can you do it?
I like fiction.
You write good fiction.

No need to chant that mantra:
"Random sample, random sample, random sample".
Just do it!

Case closed.
Well, not yet.
Now let's see what Kathy Dopp and Freeman have to say.

_____________________________________________________________

CONFIRMATION OF PRE-ELECTION AND EXIT POLL MODELS:

Total 2 party Kerry Bush
121.055 mm 59.027 62.028
Vote Percentage 48.76 51.24


2-party Vote Discrepancy
Election Model K2pty% KV BV KMargin Kerry% Kerry (mm)
Pre-election
State 51.80 62.71 58.35 4.36 -3.04 -3.68
National 51.63 62.50 58.55 3.95 -2.87 -3.47

Exit Poll
State 51.03 61.77 59.28 2.49 -2.27 -2.75
National 51.47 62.31 58.75 3.56 -2.71 -3.28
Optimizer 52.16 63.14 57.91 5.23 -3.40 -4.12

12:22am NEP (13047 respondents)
Voted 2000 Demographic

Feasible weightings
Kerry 57%/Bush 41% of New voters
100% Bush 2000 voter turnout
98% Gore turnout 52.54 63.60 57.46 6.14 -3.77 -4.57

Average 51.77 62.67 58.38 4.29 -3.01 -3.64

_________________________________________________________________


PRE-ELECTION STATE POLLS vs. EXIT POLLS vs. ACTUALS
Edited on Sat Feb-19-05 12:02 PM by TruthIsAll


The weighted national pre-election poll average (50.37%)
matched the exit poll average (50.51%).
That's 1/7 of one percent.

Total percentages are based on the weighted average.
Kerry's actual 2-party vote: 48.76% = 59028/121056

Votes and percentages are 2-party based.
Vote percentages are shown for Kerry.
Bush% = 100 - Kerry%.

Pre: final pre-election state poll average.
Exit: exit poll 2-party percentages based on data downloaded
by Simon at 12:22am Nov.3.

P/A = 100*Pre/Actual
E/A = 100*Exit/Actual

Prob: Probability of deviation
P/A Prob = pre-election poll to actual
E/A Prob = exit poll to actual

Based on the pre-election polls:
41 out of 51 states (incl DC) deviated to Bush
Based on the exit polls:
43 out of 51 deviated to Bush

Pre/ Exit/ Prob Prob Favor Favor
Vote Pre Exit Act Pre Exit Act Act Act P/A E/A Pre Exit

Total 121056 50.37% 50.51% 48.76% 60979 61144 59028 103.3% 103.6% 14.1% 12.2% 41B 43B


AK 302 34.48% 40.14% 36.77% 104 121 111 94% 109% 6.3% 1.2% K B
AL 1870 40.63% 41.08% 37.10% 760 768 694 109% 111% 0.9% 0.4% B B
AR 1043 50.00% 46.60% 45.07% 522 486 470 111% 103% 0.1% 15.4% B B
AZ 1998 47.37% 46.93% 44.72% 946 938 894 106% 105% 3.9% 7.1% B B
CA 12255 53.85% 55.73% 55.04% 6599 6830 6745 98% 101% 21.3% 32.3% K B

CO 2103 49.47% 49.07% 47.63% 1040 1032 1002 104% 103% 11.0% 16.9% B B
CT 1551 55.32% 58.47% 55.27% 858 907 857 100% 106% 48.8% 1.6% B B
DC 224 87.64% 91.63% 90.52% 197 205 203 97% 101% 2.7% 22.9% K B
DE 372 54.22% 58.44% 53.83% 202 217 200 101% 109% 39.9% 0.1% B B
FL 7548 51.55% 49.93% 47.48% 3891 3769 3584 109% 105% 0.3% 5.1% B B

GA 3280 44.68% 43.11% 41.65% 1466 1414 1366 107% 104% 2.2% 16.5% B B
HI 426 50.00% 53.32% 54.40% 213 227 232 92% 98% 0.2% 23.5% K K
IA 1494 53.19% 50.67% 49.66% 795 757 742 107% 102% 0.9% 25.0% B B
ID 590 33.71% 33.33% 30.68% 199 197 181 110% 109% 2.2% 3.8% B B
IL 5239 56.25% 57.13% 55.21% 2947 2993 2892 102% 103% 24.3% 10.0% B B

IN 2448 40.21% 40.97% 39.58% 984 1003 969 102% 104% 33.7% 17.7% B B
KS 1171 38.14% 34.60% 37.13% 447 405 435 103% 93% 25.0% 4.6% B K
KY 1782 41.05% 40.76% 39.99% 732 726 713 103% 102% 24.0% 30.6% B B
LA 1922 45.45% 44.50% 42.67% 874 855 820 107% 104% 3.2% 11.2% B B
MA 2875 70.33% 66.46% 62.74% 2022 1911 1804 112% 106% 0.0% 0.7% B B

MD 2359 55.67% 57.04% 56.57% 1313 1346 1334 98% 101% 27.5% 37.6% K B
ME 727 56.18% 54.83% 54.58% 408 399 397 103% 100% 14.4% 43.4% B B
MI 4793 53.61% 52.55% 51.73% 2569 2519 2479 104% 102% 10.5% 29.1% B B
MN 2792 54.17% 54.61% 51.76% 1512 1525 1445 105% 106% 5.4% 2.9% B B
MO 2715 47.31% 47.47% 46.38% 1284 1289 1259 102% 102% 26.7% 23.3% B B

MS 1130 45.16% 43.20% 40.49% 511 488 458 112% 107% 0.1% 3.6% B B
MT 440 38.71% 39.28% 39.50% 170 173 174 98% 99% 70.1% 44.2% K K
NC 3487 48.45% 47.31% 43.76% 1690 1650 1526 111% 108% 0.1% 0.9% B B
ND 308 38.89% 33.58% 36.09% 120 103 111 108% 93% 3.1% 4.7% B K
NE 767 34.41% 36.54% 33.15% 264 280 254 104% 110% 20.1% 1.2% B B

NH 672 50.00% 55.49% 50.69% 336 373 341 99% 109% 32.3% 0.1% K B
NJ 3581 54.35% 56.13% 53.37% 1946 2010 1911 102% 105% 25.7% 3.3% B B
NM 748 50.00% 51.34% 49.60% 374 384 371 101% 104% 39.5% 12.3% B B
NV 816 50.00% 50.66% 48.68% 408 413 397 103% 104% 19.0% 9.4% B B
NY 7277 59.38% 63.97% 59.29% 4321 4655 4314 100% 108% 47.7% 0.1% B B

OH 5599 51.55% 52.06% 48.94% 2886 2915 2740 105% 106% 4.1% 1.9% B B
OK 1464 31.46% 34.73% 34.43% 461 508 504 91% 101% 2.4% 42.1% K B
OR 1810 53.19% 51.22% 52.11% 963 927 943 102% 98% 23.5% 27.8% B K
PA 5732 52.63% 54.41% 51.26% 3017 3119 2938 103% 106% 18.0% 1.8% B B
RI 429 60.87% 64.24% 60.58% 261 275 260 100% 106% 42.3% 0.7% B B

SC 1600 43.30% 45.78% 41.36% 693 732 662 105% 111% 9.9% 0.2% B B
SD 382 44.68% 37.42% 39.09% 171 143 149 114% 96% 0.0% 13.3% B K
TN 2421 48.98% 41.15% 42.81% 1186 996 1036 114% 96% 0.0% 13.4% B K
TX 7360 38.54% 36.84% 38.49% 2837 2711 2833 100% 96% 48.6% 13.5% B K
UT 905 25.81% 29.93% 26.65% 234 271 241 97% 112% 28.6% 1.4% K B

VA 3172 47.96% 47.96% 45.87% 1521 1521 1455 105% 105% 8.1% 8.1% B B
VT 305 56.99% 65.69% 60.30% 174 201 184 95% 109% 1.4% 0.0% K B
WA 2815 54.17% 55.07% 53.65% 1525 1550 1510 101% 103% 36.4% 17.2% B B
WI 2968 53.68% 50.21% 50.19% 1593 1490 1490 107% 100% 1.0% 49.4% B B
WV 750 48.42% 45.19% 43.52% 363 339 327 111% 104% 0.1% 13.2% B B
WY 238 30.85% 32.07% 29.69% 74 76 71 104% 108% 21.9% 5.6% B B

Avg 121056 48.57% 48.84% 47.09% 60979 61144 59028 103.4% 103.8% 16.3% 9.7% B B
Median 50.00% 49.07% 47.48% 102.7% 103.9% 4.6% 9.4% B B

[TruthIsAll]

http://www.truthisall.net/THE_GRAPHS/PreExitActual.png

[davidgmills]

David:

Can't resist saying this - check it out yourself.

TIA appears to have missed the point.

Think about it:

Of course the exit polls and the pre-election polls are highly correlated. They are also highly correlated with the count. And certainly TIA's pre-election polls, like the exit polls, have Kerry higher than in the count. No contest.

But that is not what Lindeman is saying. He is saying that if the DIFFERENCE between each poll and the count are due to fraud (which is what TIA claims) then the DIFFERENCES should be correlated.

Ask TIA to plot the DIFFERENCES between his pre-election polls and the vote-count against the DIFFERENCES between the exit polls and the count. In other words, to subtract the Kerry's vote-share in the count from his response-share in each poll. That will give you two sets of "surprises" - amounts by which the Kerry's vote-share dropped relative to each poll. Plot the scatter and find the linear fit.

If the same factor - eg fraud - is responsible for both - the two sets of "surprises" should be positively correlated. Lindeman finds they aren't.

I'm looking at TIA's plot right now. If for example, fraud was responsible for the huge exit poll discrepancy in NH, you'd expect a similarly huge pre-election poll discrepancy with the count as well. But there isn't one. Kerry did slightly better in the count than in TIA's poll. Same with New York - if the Beast was in the East, and fraud was responsible for the big exit poll discrepancy in New York - how come the pre-election poll was pretty well spot on? In Massachusetts, both exit poll and pre-election poll were off - but by substantially different amounts. And in your own Tennessee, the exit poll actually understated Kerry's voteshare (you'll have to ask TIA whether it was within the MoE) but the pre-election poll predicted that Kerry would do much better than he did. In fact the pre election poll has him damn near winning Tennessee. If the reason he didn't was fraud - how come the exit polls were so close?

Anyway, the point is that the statistical check on this is a correlation between the differences, or "surprises". If the differences are not correlated it suggests that independent factors, not a shared factor, caused the discrepancies. One obvious candidate is polling error, which, seeing as the polls are conducted by different companies, are likely to be uncorrelated. For example, the exit pollsters in Tennessee may simply have done a better job than the pre-election pollsters. If the differences ARE correlated, then it suggests a common factor - eg fraud - caused the discrepancies.

I know you're not a quant, David, but you are smart. I'm not trying to fool you with credential or misleading conclusions. Just think about it, look at TIA's graph - and ask him to plot those differences.

Cheers!

Lizzie.

[TruthIsAll]

She fails to eyeball the very same RELATIVE discrepancies
she is talking about.

I compare pre and exits to the actuals using a relative index of 100
They correlate close enough for me.
But of course, they don't for her.

Will Febble dare address all the issues which OTOH disregarded?
No matter what we come up with, they obfuscate at the margins.
Try to wear us down with minutia.

Allways looking to divert and deflect.
It's so obvious.
It's so pathetic.

Such a waste.
All that talent.
Wasted on defense of Bush.

Maybe they just don't know what modeling is all about.
It's not about the trees.
It's about the forest.

Febble, get back to reality.
ONE PLAUSIBLE BUSH WIN SCENARIO.
JUST ONE.
USE THE MODEL.
If you can't provide one scenario, why should we be spending any time
listening to your tired and worn refrain?

You lost the debate.
Everyone knows the election was stolen.
Even those who do not care.

I GAVE YOU HUNDREDS OF KERRY WINNING SCENARIOS.
NOW GIVE US ONE FOR BUSH.

[davidgmills]

TIA: my email to David was not intended as a response to you, which is why I did not attempt to address your points.

However, you do appear, still, to have missed my point, which is that the DIFFERENCES between pre election polls and count and the DIFFERENCES between exit polls and count are not positively correlated WITH EACH OTHER.

I suggest you compute those differences (not the values), and plot the correlation between them, if you want to understand Lindeman's paper.

And FYI, I am not "RW". I seek truth as you do. I am a data analyst, and I am trained to ask searching questions of my data. They do not always give me the answers I would like. I do not, however, flinch from the answers, though I almost always ask further questions.

Like you, I believe that truth is the goal.

I am not a member of PI, and will not debate with you even via David unless you return the respect I accord you.

[TruthIsAll]

I respect your statistical acumen.

But your lack of experience in developing and implementing
analytical models is apparent.

They say Bush is all hat, no cattle.
I say you are all trees, no forest.
You avoid the big picture in your relentless obfuscations.

As an analyst, it's surprising that you fail to appreciate that
scores of independent models, all consistent in their confirmation,
provide an overwhelming justification for assuming that massive
election fraud occurred.

Why commit limited election fraud when
1) you need massive fraud in order to win?
2) you need massive fraud to create the illusion of a mandate?

Your argument that Kerry may have won Ohio but lost the
popular vote, betrays a profound lack of understanding in
U.S. electoral math. Democratic candidates have always done
better nationwide than in Ohio. If Kerry won Ohio, and he won the
exit poll by 4%, than he won the popular vote by at least 4%,
a SIX million vote margin.

So far, here is what we have seen from you over the past 8 months:
1. Febble Fancy Function
2. jargon, jargon, jargon
3. hypotheticals, hypotheticals, hypotheticals
4. equivocations, equivocations, equivocations

Here is what you have seen from me:
1. numbers, numbers, numbers
2. models, models, models
3. analysis, analysis, analysis
4. facts, facts, facts

Th facts:
Kerry led all the polls:
He won the undecided voters,
Nader voters, first-time voters,
voters who sat out the 2000 election,
Gore voters, females, Blacks, Hispanics,
Jews, Asians, unions, urban voters, suburban voters,
liberals, moderates, independents.

He won more Bush 2000 voters than Bush did Gore voters.
And you still believe Bush gained 13 million votes from 2000?

Tell us, dear Febble, how did he manage to do that?

Hint:
See the polling barchart timeline below.