Democratic Underground Latest Greatest Lobby Journals Search Options Help Login
Google

99.999997%. Believe.

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 » Archives » General Discussion: Presidential (Through Nov 2009) Donate to DU
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:48 AM
Original message
99.999997%. Believe.
Edited on Wed Aug-11-04 12:14 PM by TruthIsAll
It's clear that Kerry would win the election if it were held
today, based on the average polling results (let's ignore the
Electoral College for now).

The latest 15 poll average of the two-party vote (see below)
has  Kerry at 52.22%.  If this were the result of just ONE
non-biased poll (assuming a 1000 sample size) the WIN
probability would be 92%.

Now it is very expensive to do a poll. That's why national
pollsters sample just 1,000 voters nationwide. This sample
size produces a margin of error (MoE) of 3%. This means that
if Kerry has a poll mean of 52.22%, there is a 95% probability
that he will get between 49.22% and 55.22% of the vote.

But we have FIFTEEN polls, not just ONE. Running 15 polls,
each with a sample size of 1,000 taken from the SAME voting
population of over 150 million registered voters, is
equivalent to running a SINGLE poll of 15,000. The current
Kerry statistical MEAN for the 15 polls is 52.22%. 

But the margin of error (MoE) around the mean is lower than
3%, because our sample size is now 15,000, not 1,000. In fact,
the MoE for a 15,000 sample size is a tight +/-0.80%. This
means there is a 95% probability that Kerry will get between
51.42% and 53.02% of the vote (a much smaller confidence
interval) were it held today. 

Ok, but we want to know what is the probability that Kerry
will get OVER 50% of the 2-party vote (just vs. Bush),
assuming a 15,000 sample size (or, equivalently, for 15 polls,
each with a 1,000 sample size)?

The answer is 99.999997%. You heard it here first.

Take a look at the following 15 individual polls. Then check
the probability matrix. This shows the probability of a Kerry
win over a range of polling averages (from 50.5% to 55.0%,
including his actual current 52.22% mean), over a range of
polling sample sizes, ranging from 1,000 to 15,000.

What's the point of all this? Simple. Kerry is in a much more
commanding position than the individual polls would indicate.
In fact, he is a SURE THING if, and its a big IF, the election
were held today.

			
Latest Poll Results	Kerry%							
Date	Poll	Kerry	Bush	2-pty	MoE	
807	TIME	51	43	0.543	3.0	
804	FOX	46	43	0.517	4.0	
801	CNN	48	48	0.500	4.0	
721	LAT	48	46	0.511	3.0	
718	PEW	46	44	0.511	3.0	
												
806	IBD	49	43	0.533	3.5	
730	CBS	49	43	0.533	3.0	
805	DEMC	52	45	0.536	3.1	
802	ABC	52	45	0.536	3.0	
730	NWK	52	44	0.542	4.0	
												
729	ZOG	48	43	0.527	3.2	
806	AP	48	45	0.516	3.5	
721	NBC	45	47	0.489	3.4	
801	ARG	49	45	0.521	3.5	
722	QPAC	46	43	0.517	2.5	
												
												
N	1000											
Mean		48.60%	44.47%	52.22%	3.31%	
Median      48.00%	44.00%	52.13%	3.20%	
												
MoE	3.31%											
Std	1.690%										

If n= sample size,
MoE =1.96 / (2*sqrt(n))									
Std (standard deviation) =.5 / sqrt(n)	

	WIN PROBABILITY (AT LEAST 50% OF POP. VOTE)				
			(based on sample size and mean)									
												
Sample Sample Std	    Percent of two-party vote			
Size	MoE	Dev	50.5%	51.0%	52.0%	52.22% 53.0% 54.0%	55.0%			
												
					Win Probability Matrix						
600	4.00%	2.04%	59.7%	68.8%	83.6%	86.2%	92.9%	97.5%	99.3%
1000	3.10%	1.58%	62.4%	73.6%	89.7%	92.0%	97.1%	99.4%	99.9%
2000	2.19%	1.12%	67.3%	81.4%	96.3%	97.6%	99.6%	100.0% 100%
3000	1.79%	0.91%	70.8%	86.3%	98.6%	99.2%	99.9% 100.0% 100%
4000	1.55%	0.79%	73.6%	89.7%	99.4%	99.8%	100.0% 100.0% 100%
5000	1.39%	0.71%	76.0%	92.1%	99.8%	99.9% 100.0% 100.0% 100%

6000	1.27%	0.65%	78.1%	93.9%	99.9%	100.0% 100.0% 100% 100%
7000	1.17%	0.60%	79.9%	95.3%	100.0	100.0% 100.0% 100 %100%	
8000	1.10%	0.56%	81.4%	96.3%	100.0	100.0% 100.0% 100% 100%	
9000	1.03%	0.53%	82.9%	97.1%	100.0	100.0% 100.0% 100% 100%	
10000	0.98%	0.50%	84.1%	97.7%	100.0 100.0% 100%.0 100% 100%

11000	0.93%	0.48%	85.3%	98.2%	100.0% 100.0% 100% 100%	100%
12000	0.89%	0.46%	86.3%	98.6%	100.0% 100.0% 100% 100%	100%
13000	0.86%	0.44%	87.3%	98.9%	100.0% 100.0% 100% 100%	100%
14000	0.83%	0.42%	88.2%	99.1%	100.0% 100.0% 100% 100%	100%
15000	0.80%	0.41%	89.0%	99.3%	100.0% 100% 100% 100% 100%
Printer Friendly | Permalink |  | Top
gasperc Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:54 AM
Response to Original message
1. too bad election isn't today
with the Iran war resolution getting ginned up, it's going to be a longgggggggggggggggg fall.
Printer Friendly | Permalink |  | Top
 
Feanorcurufinwe Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 12:09 PM
Response to Reply #1
5. Disagree, we need the extra time to build momentum so we can take Congress
Printer Friendly | Permalink |  | Top
 
UrbScotty Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:58 AM
Response to Original message
2. Odds of Kerry not getting 50%: 3 in 100,000,000, folks. (nt)
Printer Friendly | Permalink |  | Top
 
On the Road Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 12:02 PM
Response to Original message
3. The Only Unknowns in All This
are response variables and turnout. In other words, the analysis is valid assuming that (1) people will vote the way they responsd to the poll and (2) the poll sample is a good representation of the voters who will show up on election day. These are much bigger questions than the margin-of-error business.

I think Kerry is going to win, too. I think both turnout and response-variable issues work in Kerry's favor, and that Kerry may win by more than the margin shown in the polls.

But the 2002 elections showed that surprises happen, and they're not always favorable to Democrats. Just a word of caution.

Printer Friendly | Permalink |  | Top
 
Feanorcurufinwe Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 12:08 PM
Response to Original message
4. Believe
Printer Friendly | Permalink |  | Top
 
Zynx Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 12:11 PM
Response to Original message
6. I just completed a state by state population vote tabulation and I agree.
Edited on Wed Aug-11-04 12:50 PM by Zynx
I'll get the results up tonight if I can.

What I did was take state by state polls and multiplied the percents by the projected number of voters and came up with some rough numbers.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 01:52 PM
Response to Reply #6
7. We only need the latest 5 national polls to approach 100% win prob.
Edited on Wed Aug-11-04 01:53 PM by TruthIsAll
WIN PROBABILITY (AT LEAST 50% OF POP. VOTE)				
(based on sample size and mean)																			
Win Probability Matrix								

Sample Sample Std	    Percent of two-party vote			
Size	MoE	Dev	50.5%	51.0%	52.0%	52.22% 53.0% 54.0% 55.0%		

600	4.00%	2.04%	59.7%	68.8%	83.6%	86.2%	92.9%	97.5%	99.3%
1000	3.10%	1.58%	62.4%	73.6%	89.7%	92.0%	97.1%	99.4%	99.9%
2000	2.19%	1.12%	67.3%	81.4%	96.3%	97.6%	99.6%	100.0%
3000	1.79%	0.91%	70.8%	86.3%	98.6%	99.2%	99.9% 100.0% 
4000	1.55%	0.79%	73.6%	89.7%	99.4%	99.8%	100.0% 
5000	1.39%	0.71%	76.0%	92.1%	99.8%	99.9% 100.0% 

6000	1.27%	0.65%	78.1%	93.9%	99.9%	100.0% 
7000	1.17%	0.60%	79.9%	95.3%	100.0	
8000	1.10%	0.56%	81.4%	96.3%	100.0	
9000	1.03%	0.53%	82.9%	97.1%	100.0	
10000	0.98%	0.50%	84.1%	97.7%	100.0 

11000	0.93%	0.48%	85.3%	98.2%	100.0% 
12000	0.89%	0.46%	86.3%	98.6%	100.0% 
13000	0.86%	0.44%	87.3%	98.9%	100.0% 
14000	0.83%	0.42%	88.2%	99.1%	100.0% 
15000	0.80%	0.41%	89.0%	99.3%	100.0% 
Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 01:57 PM
Response to Original message
8. Bad Assumption
Your analysis assumes that undecided voters are going to break in the same ratio as the decides. That's a foolhardy assumption.
Printer Friendly | Permalink |  | Top
 
SidDithers Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:43 PM
Response to Reply #8
10. Don't undecideds usually break away from the incumbent...
and toward the challenger? If that's the case, TIA is understating the effect of undecideds.

Sid
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 08:51 PM
Response to Reply #10
25. Sorry, My bad. I misread your post. Undecided break toward the challenger.
In my daily national/state simulation model, I assume a 70% break for Kerry.

In this analysis, I wish to keep it simple by being conservative and assuming undecided/nader/other allocation proportional to current polling.

On that basis alone, Kerry will do better than 52.22%.

I expect him to approach 54%.
Printer Friendly | Permalink |  | Top
 
Feanorcurufinwe Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:50 PM
Response to Reply #8
13. WTF? That is a very pessimistic assumption.
Edited on Wed Aug-11-04 02:51 PM by Feanorcurufinwe
Since historically, undecideds actually break heavily towards the challenger.

Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:32 PM
Response to Reply #8
16. No, sir, I do not assume it, even though it is true.
You obviously are unfamiliar with the fact that historically challengers have recievedd the bulk of the undecided vote.

I dare you to prove otherwise.
Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:02 PM
Response to Reply #16
27. Nope
I simply think that assuming anything about how undecideds will break will have a significant effect on the margin of error.

I dare you to prove otherwise.
Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:38 PM
Response to Reply #27
28. You can look at historical data to make the assumption.
After all, doing a poll in the first place is assuming that the overall population is represented in the sample, and historically, that has been proven to be correct, if the poll is done correctly.

Nothing wrong with assuming how the undecideds will break, based on historical data of how they have broken in the past.

Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 09:59 AM
Response to Reply #28
31. Good point
If you look at the historical data and run this type of analysis you'll see that its complete bullshit. If you took the poll numbers put put by all the polling companies a few days before the 2000 election and ran it through TIA's algorithm you'd come to the conclusion that there was a 99.9% George Bush would win a majority of the popular vote. That of course, didn't happen which proves that this type of analysis is completely wrong headed.
Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 10:19 AM
Response to Reply #31
35. What's that got to do with anything?
My point was that there is historical data to show in what percentage the undecided voters tend break for the incumbent, and what percentage they tend to break for the challenger.

Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 11:14 AM
Response to Reply #35
37. And my point
Is that there is historical data that proves TIA's methodology is seriously flawed.

Don't you think that's significant?
Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 12:17 PM
Response to Reply #37
38. As I said, I'm just discussing the fact that there
is historical data to show how undecideds will break in an election and the percentages that historically break for the challenger as opposed to breaking for the incumbent.

What TIA does in his number-crunching is a different topic.

Just because you disagree with TIA's methodology doesn't mean that the historical data regarding undecideds is unreliable.


Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 12:48 PM
Response to Reply #38
39. Ok
To sum up then:

1) There is historical data that shows that undecideds break for the challenger.
2) There is historical data that shows that TIA's methodology is flawed.

Both of these statements are true.
Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 01:19 PM
Response to Reply #39
40. All along I have just been talking about the first statement.
You keep talking to yourself about the second statement.

Printer Friendly | Permalink |  | Top
 
Nederland Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 01:26 PM
Response to Reply #40
41. My mistake
I though the topic of this thread was whether or not it was actually true that Kerry had a 99.999997% chance of winning, not whether or not undecideds historically break for the challenger.

I apologize.

Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 02:23 PM
Response to Reply #41
42. Interestingly enough, thread topics often have subtopics underneath them
Edited on Thu Aug-12-04 02:26 PM by Lex
and you can tell those sub-topics by looking at how the main topic is threaded, and sub-threaded, and so on.

The sub-threads are related to the main topic, but not all sub-threads are directly on point with the overall thread topic.

For example, I was only addressing the fact that historical data has been collected and can be used to predict how undecideds will break.


Printer Friendly | Permalink |  | Top
 
beyurslf Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:30 PM
Response to Original message
9. That isn't really a big "IF" it is an impossiblity
since the election is scheduled by the Constitution.
Printer Friendly | Permalink |  | Top
 
Barret Donating Member (183 posts) Send PM | Profile | Ignore Wed Aug-11-04 08:15 PM
Response to Reply #9
23. Ummm....
Actually the constitution does NOT provide any date for any election. Please point out where it does. I really wish people would actually READ the constitution. It takes about 30 minutes and then you will actually know what it does and does not say.

Actually the election dates were set in federal law back in the 1800's. Which is a power granted to congress in the constitution. (to decide the time, places, and manner in which elections will be held)

Alaska (under federal law) can actually have it's election a month or two earlier if it anticipates bad weather that could limit peoples ability to vote.
Printer Friendly | Permalink |  | Top
 
SidDithers Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:44 PM
Response to Original message
11. Nice analysis...
I enjoy reading your posts - and look forward to more :)

Sid
Printer Friendly | Permalink |  | Top
 
Tweed Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:46 PM
Response to Original message
12. Yawn....
Isn't this the same info we've been getting for the past three weeks?
Printer Friendly | Permalink |  | Top
 
Feanorcurufinwe Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 02:51 PM
Response to Reply #12
14. No.
You need to read more carefully.
Printer Friendly | Permalink |  | Top
 
Tweed Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 06:54 PM
Response to Reply #14
15. I did read it carefully
I'm aware that the info is from today, but it's basically the same from three weeks ago and it's still as pointless as it was when it started.
Printer Friendly | Permalink |  | Top
 
TruthIsAll Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:34 PM
Response to Reply #15
17. Same old tweed; just stop reading it, no one is forcing you.
Why do you keep coming back?

Could it be you really like me?
Printer Friendly | Permalink |  | Top
 
Zynx Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:35 PM
Response to Reply #17
18. I bet he does.
;-)
Printer Friendly | Permalink |  | Top
 
Tweed Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:36 PM
Response to Reply #17
19. There is a 99.99999999997 percent chance I think your model is bullshit
and I think you need to be called on it
Printer Friendly | Permalink |  | Top
 
ALago1 Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:39 PM
Response to Reply #19
20. I'm not a statstics aficianado
So, I don't want to get my hopes up due to this one analysis.

But, I think that the argument put forth is very convincing.

So, if you disagree, why not tell us what you think is wrong with the methodology?
Printer Friendly | Permalink |  | Top
 
Zynx Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 07:41 PM
Response to Reply #19
21. IF the election were held today, there is little doubt that Kerry would
win. That's the thrust of this. Take from that what you will.
Printer Friendly | Permalink |  | Top
 
Name removed Donating Member (0 posts) Send PM | Profile | Ignore Wed Aug-11-04 07:50 PM
Response to Reply #19
22. Deleted message
Message removed by moderator. Click here to review the message board rules.
 
Tweed Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 10:41 PM
Response to Reply #22
26. What's my analysis? That these polls don't help anything.
John Kerry would win today? Great! Dukakis would have won too had the election been right now. All these numbers do is get people over confident. Anything could happen to change the outcome of the numbers.

One posting showing these numbers, cool. But once a day? Twice a day? Then people just get the idea of "Oh Kerry will win for sure." It's very dangerous to think so. We must keep the fight going and the hunger alive. I appreciate the time that you put into this, but it ultimately doesn't do anyone any good.

I don't need a degree of any kind to tell you that much. Hell a kid with a degree from kindergarten could tell you that what is the case today doesn't mean anything Nov. 2nd.

Truth is all. Math is not. Logic is all.
Printer Friendly | Permalink |  | Top
 
Zynx Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 10:03 AM
Response to Reply #26
32. The comparisons to Dukakis are ridiculous.
I really wish people would stop using them. In that campaign, both candidates had rather low name recognition in terms of people having an opinion one way or the other. That was a typical challenger/challenger race despite Bush Sr. being the VP. Thus, there were extremely volatile numbers. This is a challenger vs. Incumbent race, which is COMPLETELY different. All the formulas and historical models are dramatically different than in challenger/challenger race.
Printer Friendly | Permalink |  | Top
 
Merlin Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 08:40 PM
Response to Original message
24. Thanks for the good work, TIA.
I needed that stat refresher, too.
Printer Friendly | Permalink |  | Top
 
Lex Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:40 PM
Response to Reply #24
29. I agree. Thanks TIA!
I appreciate the work you do in crunching these numbers!

Printer Friendly | Permalink |  | Top
 
tblue37 Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Aug-11-04 11:41 PM
Response to Original message
30. I am ignorant about statistics,
but even if Kerry wins the popular vote, that doesn't mean he wins the presidency. It's <i>where</i> the votes are that matters. If most people in the US believe he would win now, doesn't that mean about the same as having "most" people vote for him? After all, most people voted for Al Gore in the last election.

Does this set of statistics show Kerry winning the electoral vote?
Printer Friendly | Permalink |  | Top
 
Zynx Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 10:04 AM
Response to Reply #30
33. If he won by that margin nationally, he would win over 320 EVs.
Edited on Thu Aug-12-04 10:05 AM by Zynx
States can't vote completely independent of national trends. It just doesn't work that way. Sure you get your occasional race where someone narrowly wins the electoral college, but loses the popular vote, but that's rare for a reason.
Printer Friendly | Permalink |  | Top
 
swag Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 10:10 AM
Response to Original message
34. Princeton Sam has a very similar number to yours
Printer Friendly | Permalink |  | Top
 
PATRICK Donating Member (1000+ posts) Send PM | Profile | Ignore Thu Aug-12-04 10:25 AM
Response to Original message
36. More than numbers
which I expect to mirror the situation anyway. The "Dukakis comfort" that the media tools and wistful GOP cling to is that polls don't count. Or the Truman that couldn't be wished away by the media who didn't bother even to ask the people as one in a long string of their preferences and picks went down in humiliating defeat.

Dukakis was riding the shoulders of the party. Kerry is carrying us pretty well on his own, increasing in strength, campaigning wisely, strongly, taking the punches not like a punching bag but like a fighter.

Now polls that show comparable numbers have to take into account what is really going on in the contemporary hearts and minds of those numbers. Republicans hate Bush as do some of the military in his LOSING popular base from last time.

Without breaking a smile the media cringingly reports on Bush's outreach to the AMISH and Christian fundies, the last groups who will never have seen F9/11, the now disappeared missing element from the voters' knowledge base.

We know two things. Kerry, given a fair campaign would pound Bush into electoral dust. That is so easy to predict no compendium of data is needed. Second it will not be fair and any craziness is more acceptable than "honorable" defeat for Bushco. The polls are mainly a sideshow to this blunt reality, which must be worked out, as the polls in the weeks ahead.
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 Thu May 02nd 2024, 10:57 PM
Response to Original message
Advertisements [?]
 Top

Home » Discuss » Archives » General Discussion: Presidential (Through Nov 2009) 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