BUSH HAS WON!!!!
POSTED BY: Anarko
UPDATED: Wednesday, December 29, 2004 10:18
VIEWED: 18245
PAGE 6 of 9
(buzzer) wrong! 100% confidence interval represents the exact population. It can happen when your samples *are* the population.
Gimme a break, you had to go to a webpage and you don't understand it even after you read it.
95% confidence interval is what is used regularly for normal everyday meaningless polls like "Do you listen to Avril or Brittany more?". Critical studies like this one published should have used at least a 98% confidence interval. But too bad, their procedures wouldn't have allowed them that. Their interval would have been 600-2000000 with 98% CI, instead of that pretty damn ludicrous and unbelievable 8000-194000.
See how this works? To narrow the possible interval, your confidence goes down with the same figure. So if you narrow the interval to say 10000-150000, then your confidence level goes down to 80%. 50000-130000, prolly around 65%. By the time you get down to specifying the exact median. It's something like 0.02% confidence that it would be that 100000 figure.
Yeah, I agree. It's pretty useless as far as numbers go. You can take that report to anyone with rudimentary understanding of statistics (even a poorly taught first year stat class would clearly explain this concept. Well, at least you shouldn't have been let pass the class without understand this)
Not only were the study, the procedure used in the study *and* the report itself flawed. But the analysis and the media report are highly flawed and misleading, bordering on criminal.
Quote:
Originally posted by rue:
"For those not versed in statistics, that means that the researchers were 95% confident (not even 100%)"
I suspect you don't know statistics either. A 100% confidence interval is an invalid figure. You should not have brought it up.
http://techniques.geog.ox.ac.uk/mod_2/glossary/confint.html
Like Fireflyfans.net?
Haken needs a new development system. Donate.
http://www.fireflyfans.net/thread.asp?b=5&t=3283
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
It depends on your measure - counting or continuous.
PS We've had the debate before, I believe, and this is where it got stuck last time.
NOTIFY: N | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Many exit polls did not match the final vote:
http://www.reuters.com/newsArticle.jhtml?type=industryNews&storyID=670
7692
"'We have an exit poll crisis,'said pollster John Zogby, whose own Election Day predictions that Kerry would take Ohio and Florida proved wrong. He said he had used the exit poll data to confirm conclusions he had based on his own polling."
http://www.mercurynews.com/mld/mercurynews/news/special_packages/elect
ion2004/10092541.htm?1c
"But the polling consortium used by the networks and The Associated Press came under scrutiny Wednesday for exit polls that showed President Bush trailing Sen. John Kerry in battleground states throughout Election Day."
Also, after voting closes, exit polls are adjusted to the vote tally.
"After the survey is completed and the votes are counted, the exit poll results are adjusted to reflect the actual vote, which in theory improves the accuracy of all the exit poll results, including the breakdown of the vote by age, gender and other characteristics."
http://www.washingtonpost.com/wp-dyn/articles/A23580-2004Nov3.html
That may be the reason for the congruence between the final CNN exit poll and the final vote in Florida, while real-time exit polls indicated a different outcome.
Which still leaves the question open - was the exit polling flawed, or was it the vote count? I haven't come down on either side, I would find a statistical study enlightening. I'm going to keep my eyes open to see if one comes out.
NOTIFY: N | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
no! there is only a difference in that if you are actually sampling!
If your samples *are* your population, you are no longer sampling. You can still calculate mean, and deviations, and the normal statistics. But when your samples *are* your population, there is no confidence level. It is 100% by definition and all means of it.
Quote:
Originally posted by rue:
It depends on your measure - counting or continuous.
PS We've had the debate before, I believe, and this is where it got stuck last time.
Like Fireflyfans.net?
Haken needs a new development system. Donate.
http://www.fireflyfans.net/thread.asp?b=5&t=3283
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Err... there isn't any exit poll disparity... The only problem is with people (sigh) getting early data and stupidly reporting on them as real figures without understanding the reasoning of their inaccuracies.
read the article excerpts that points it out here:
Quote:
To compound the problem further, a server at Edison/Mitofsky malfunctioned shortly before 11 p.m. The glitch prevented access to any exit poll results until technicians got a backup system operational at 1:33 a.m. yesterday.
The crash occurred barely minutes before the consortium was to update its exit polling with the results of later interviewing that found Bush with a one-point lead. Instead, journalists were left relying on preliminary exit poll results released at 8:15 p.m., which still showed Kerry ahead by three percentage points.
It was only after the polls had closed in most states and the vote count was well underway in the East that it became clear that Bush was in a stronger position in several key battlegrounds, including Ohio, than early exit polls suggested.
Some problems are inevitable. A total of 12,047 randomly selected voters were interviewed Tuesday as they left their polling places, and those results were fed into computers. The accumulated results were reported several times over the course of Election Day.
Results based on the first few rounds of interviewing are usually only approximations of the final vote. Printouts warn that estimates of each candidate's support are unreliable and not for on-air use. Those estimates are untrustworthy because people who vote earlier in the day tend to be different from those who vote in the middle of the day or the evening. For instance, the early national sample Tuesday that was 59 percent female probably reflected that more women vote in the day than the evening.
That is why the early leaks anger Lenski. "The basic issue here is the leaking of this information without any sophisticated understanding or analysis, in a way that makes it look inaccurate," he said.
Quote:
Originally posted by rue:
Many exit polls did not match the final vote:
http://www.reuters.com/newsArticle.jhtml?type=industryNews&storyID=670
7692
"'We have an exit poll crisis,'said pollster John Zogby, whose own Election Day predictions that Kerry would take Ohio and Florida proved wrong. He said he had used the exit poll data to confirm conclusions he had based on his own polling."
http://www.mercurynews.com/mld/mercurynews/news/special_packages/elect
ion2004/10092541.htm?1c
"But the polling consortium used by the networks and The Associated Press came under scrutiny Wednesday for exit polls that showed President Bush trailing Sen. John Kerry in battleground states throughout Election Day."
Also, after voting closes, exit polls are adjusted to the vote tally.
"After the survey is completed and the votes are counted, the exit poll results are adjusted to reflect the actual vote, which in theory improves the accuracy of all the exit poll results, including the breakdown of the vote by age, gender and other characteristics."
http://www.washingtonpost.com/wp-dyn/articles/A23580-2004Nov3.html
That may be the reason for the congruence between the final CNN exit poll and the final vote in Florida, while real-time exit polls indicated a different outcome.
Which still leaves the question open - was the exit polling flawed, or was it the vote count? I haven't come down on either side, I would find a statistical study enlightening. I'm going to keep my eyes open to see if one comes out.
Like Fireflyfans.net?
Haken needs a new development system. Donate.
http://www.fireflyfans.net/thread.asp?b=5&t=3283
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Quote:
If things don't improve in the U.S. now that the repubs hold all the cards, their party will be exposed for the corporate/christian right tools they are and 2006 / 2008 will not be pretty for them.
Yer new to this whole politics hugamuga, ain't ya?
NOTIFY: N | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Quote:
Originally posted by Ghoulman:Quote:
Originally posted by lissa:
i think i'm going to cry.
i changed my mind. i'm moving to canada.
and then i'm crying.
~lissa, spwhore
Need a roomate?
Don't get so crazy, it's not the end of the wor... oh wait. Never mind.
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Quote:
Originally posted by lissa:
i think i'm going to cry.
i changed my mind. i'm moving to canada.
and then i'm crying.
~lissa, spwhore
You wanna carpool? Gas prices are way to high to go alone ;)
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
Oh yeah one more thing, those who think Bush did good. In my country (The Netherlands) governments have stepped down themselfes for far less horrible things then Bush.
And my country ranks higher on that website then the US. (nanananananaaa! sorry...)
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME
@Daikath
No wonder are the netherlands such a good country to live in, when the consumation of marihuana is legal. 
But I think switzerland will soon be the second country in europe where it will be legalized.
Anyway. I think we'll see us in four years when it's:
Arnold Schwarzenegger vs. Hillary Clinton
And to all americans: Only 1538 days left....
-----------------------------
Yes there are Fireflyfans all over the world. Even in little switzerland.
NOTIFY: Y | REPLY | REPLY WITH QUOTE | PERMALINK | TOP | HOME