TruthIsAll
(1000+ posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 02:44 AM
Original message |
BASED ON EXIT POLLS, THE PROBABILITY KERRY WOULD LOSE OH AND FL = 0.15% |
|
That's less than 1/6 of one percent!
To put it another way, the chances are 1 out of 667 that Bush would win BOTH states.
Assuming a 2% MoE for the exit polls (they are much more accurate than standard polls), the probabilities are:
Ohio Exit Poll: Kerry 52 - Bush 48 Prob (Kerry wins OH)= 97.7%
Florida Exit Poll: Kerry 51 - Bush 48 Prob (Kerry wins FL)= 93.5%
Then Prob (Kerry loses FL and OH) =0.15% = (1-.977)*(1-.935)
Prob(Kerry wins OH or FL or Both)= 99.85% = 1 -.15%
How did I calculate the probs? Simple. Feed the data into the Excel Normal Distribution function:
Since the MoE = .02, the Standard Deviation is .02/1.96 = .01
Prob (Kerry wins OH)= NORMDIST(0.52,0.5,0.01,TRUE) = 97.7%
Prob (Kerry wins FL)= NORMDIST(51/99,0.5,0.01,TRUE) = 93.5%
|
Awsi Dooger
(1000+ posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 03:38 AM
Response to Original message |
1. Maybe the offshore sportsbook will give me my money back |
|
Plus the profit on Kerry.
I don't know about these exit polls. Since all of them seemed to overstate Kerry's numbers, and he had tiny projected leads in FL and OH, I tend to think Democrats simply voted early and the samples were screwed up. I checked a few sources and Kerry's early numbers went down as the day went on, including FL and OH. I want to look at them further.
The same thing happened in 2002, if you remember. Some of the same states. Early exit polls from Colorado and North Carolina and New Hampshire and Florida greatly overstated how Democrats were doing in senate and governor races.
Again, I hate to condemn or eliminate electronic voting because it should help us, not hurt us, in urban areas if the count is legit. I voted on touch screen in Nevada, after years of punch cards in Florida. No comparison in ease of use, or ability to double check. I need to find out if the paper trail, which looks like a continuous grocery receipt, will be checked, or has been checked, to verify the machine tally. IMO that should always be done, regardless of margin.
|
JI7
(1000+ posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 03:46 AM
Response to Reply #1 |
2. Kerry had huge support from young voters |
|
and if young people are voting they tend to be the enthusiastic and informed type. the type who would be excited and want to get out there as early as they can when polls open.
|
Radio-Active
(735 posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 08:10 AM
Response to Original message |
klyon
(1000+ posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 10:02 AM
Response to Original message |
|
I thought they were outlawed. KL
|
YouLiedTheyDied
(49 posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 10:48 AM
Response to Original message |
|
The exit polls were garbage. They were conducted early in the day, they oversampled our voters... especially women. It was the height of irresponsibility of that hack Drudge to release them. The numbers were bad. I'm sorry, I've run several races including state Senate races, and there is a flow of voters. They are inherently flawed if taken early because there is not enough time for a decent demographic distribution. These polls were done by noon to be released by 1:30. In NYS that would have been less than half of the time the polls were open, and would not have captured the lunch time voters or after work crowd, which is when thugs vote. I know, I've also served as a poll inspector for the state in every major city in our state and those trends hold tight. Early morning and morning voters are heavily democratic. Lunch time mix with more thugs. Afternoon a lot of moms and grandparent types and this year students. Afterwork and early evening is heavily thug. That's just the way it goes. Those exit polls were bullshit.
|
Awsi Dooger
(1000+ posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 07:36 PM
Response to Reply #5 |
6. Thank you, that's informative |
|
I've only looked at internet-released early exit poll numbers in 2002 and 2004, but in that brief sample everything you state holds up. In 2002, the first Drudge exit poll from Colorado had the Democratic senate candidate, Strickland, up something like 19 points. Insane. He lost by 6.
This is hardly backfitting rationalization to validate this year's result. I was working GOTV Tuesday, but before sleep Monday night I posted a warning thread in this forum, specifically mentioning four lousy early exit poll numbers from 2002, and that DUers should not go overboard regarding Drudge's early numbers, one way or another.
I didn't realize until this week, and descriptions like yours, that Democrats tend to vote very early.
|
KerryDownUnder
(73 posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 08:03 PM
Response to Original message |
7. The Person From the Exit Polling Firm Said |
|
that their later exit polls on election day showed Bush winning Ohio by 1%. I just heard him on the radio. He was PO'd that the earlier data had been released and was trying to make the argument that they weren't far off but that everyone is focusing on early results rather than all the results.
Making an argument about the final results not lining up with the exit polls seems valid, but if the exit polls everyone is using doesn't represent their final result then the whole exercise is kind of pointless.
|
bagnana
(858 posts)
Send PM |
Profile |
Ignore
|
Sun Nov-07-04 08:25 PM
Response to Reply #7 |
8. thank you. I didn't hear that. |
|
Somehow it would bother me much more to hear that exit polling was completely off. Where the hell is this information anyways? I can't find it online.
|
DU
AdBot (1000+ posts) |
Fri Apr 26th 2024, 04:22 AM
Response to Original message |