Talk:Exit poll

From Wikipedia, the free encyclopedia
Jump to: navigation, search
WikiProject Elections and Referendums  
WikiProject icon This article is within the scope of WikiProject Elections and Referendums, an ongoing effort to improve the quality of, expand upon and create new articles relating to elections, electoral reform and other aspects of democratic decision-making. For more information, visit our project page.
 ???  This article has not yet received a rating on the quality scale.
WikiProject Politics (Rated Start-class, Mid-importance)
WikiProject icon This article is within the scope of WikiProject Politics, a collaborative effort to improve the coverage of politics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
Start-Class article Start  This article has been rated as Start-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.


And there's the fresh Venezuela case.[1] A win-win for the US, of course. Either their "polls" succeed in swaying the vote or provide "evidence" the vote was rigged. 03:42, 20 Aug 2004 (UTC)

Funded by the NED[2] - thought so. 16:14, 20 Aug 2004 (UTC)

NPOV dispute[edit]

See 2004 U.S. presidential election controversy, exit polls, and esp. 2004_U.S._presidential_election_controversy,_exit_polls#USCountVotes. Also see Bayesian and conditional probability. Kevin Baastalk 21:15, 2005 Feb 23 (UTC)

UK polls banned[edit]

I would like to request a citation alert for the sentence in this article that suggests that UK opinion polls are banned. Harry Hayfield 17:25, 21 October 2006 (UTC)

Why do media organizations restrict exit poll results during elections?[edit]

I've noticed that media organizations don't release exit poll results during an election. Is this voluntary, or the result of a law? The timing of exit poll releases would be helpful in the article. -- Creidieki 18:10, 7 November 2006 (UTC)

In the US it's a voluntary withholding, in large part due to how bad the 2004 exit polls were. The raw exit poll leaked to the Drudge Report and other political bloggers mid afternoon and it turned out the demographics of that exit poll were several percentage points off on the demographics of those who voted. (Ratio of Females to Males; Age breakdown; Singles to Married; etc ) Now the major news media tended to use the final adjusted for demographic exit polls for projecting results early on election night, but eventually one by one they determined it wasn't accurate enough when they compared the actual results in these precincts to the exit polls for the precincts and purged the exit poll data from the projection systems. (As I recall, that adjusted was within normal margin of error but in a close election 2 1/2 percentage points just isn't good enough.) There were a long list of theories these exit polls could have been off, including the limited number of hours the exit polls were (in general during morning work hours), perhaps those too busy to take an exit poll were disproportionately from one political party, and in some states large percentage of early voting and/or vote by mail. 20:59, 7 November 2006 (UTC)
The National Election Pool (NEP) exit poll (conducted by Edison Research) voluntarily releases the data when all of the polls have closed. It is important to consider that exit poll results that were 'leaked' to various web sites during the mid-afternoon should be taken with a very big grain of salt. It is like trying to determine the winner of the Super Bowl based on the half-time score. The numbers that are released during the mid-afternoon are not in real-time by the time you might see those 'leaked' numbers they could very well be three of four hours old.—Preceding unsigned comment added by (talk) 11:54, 31 January 2009

Bradley Effect[edit]

No mention of the Bradley Effect on this page? (I could not remember the name of this phenomenon so I came to the exit poll page; it took some additional digging to uncover the name. —Preceding unsigned comment added by (talk) 17:10, 17 January 2008 (UTC)

A better term for the word "Bradley effect" would be "disparity." It is the result of oftentimes people comparing the MOST favorable or unfavorable poll result of a candidate to the election result; of course there will be a discrepancy in that case, because polls have a margin of error and you won't get the same result with each poll. If you however take the AVERAGE result of election polls, and compare them to the end result, you will be stunned by just how remarkably accurate these polls are. Here are some links for emphasis.
Polling organizations predicted Obama to receive 52.1% of the popular vote; he receives 52.9. They also predict the margin of the election to be 7.6% points, it is 7.3%; likely because supporters of 3rd parties dumped a minute percentage of their votes for McCain (a candidate that has a better shot at winning). [3] Notice that though Obama received 52.9% of the popular vote, it is expected that some will underestimate his support at 50%, some will overestimate at 55%. In any case, his support was AT MOST overestimated by 55-52.9 = 2.1%, sometimes underestimated to be 50-52.9 = -2.9%. Even if we take that end result, there's hardly a "Bradley effect," because polls have an expected margin of error as well. To sample a few hundred or a few thousand people in each state, and accurately predict the end result of millions of people is a complex art and science, and these are professional polling organizations doing work.
Here is the exit polling for Florida Amendment 2 compared to the actual election result. [4]
Here is the exit polling of similar propositions in Arkansas, Arizona, California. [5] [6] [7] Keep in mind that these are controversial issues where people are oftentimes thought to give to give politically correct responses to interviewees. When you look at the data, there is NO DIFFERENCE between the exit polling and election result! Literally none, as in 0%.
For a layman to say that what PROFESSIONAL polling organizations do is inaccurate is at best ignorant, and at worst blasphemous! --rock8591 03:06, 24 October 2009 (UTC)

What's the source?[edit]

"A famous example of exit poll error occurred in the 1992 UK General Election, when two exit polls predicted a hung parliament."

I've read a good deal about exit polls, and never heard of this, so it's certainly not famous. My question though is did this even happen? What is your source? —Preceding unsigned comment added by Buon professore (talkcontribs) 06:14, 23 September 2008 (UTC)

Removed section (Problems)[edit]

There is not a citation in this section. I had asked about a citation a month ago, but no one replied. I was, and still am particularly curious about this purported 1992 error.

"A famous example of exit poll error occurred in the 1992 UK General Election, when two exit polls predicted a hung parliament. The actual vote revealed that Conservative Party Government under John Major held their position, though with a significantly reduced majority."

--Buon professore (talk) 03:18, 21 October 2008 (UTC)

Explanation, please[edit]

"Like all opinion polls, exit polls by nature do include a margin of error. A famous example of exit poll error occurred in the 1992 UK General Election, when two exit polls predicted a hung parliament. The actual vote revealed that Conservative Party Government under John Major held their position, though with a significantly reduced majority.

A more fundamental statistical problem with exit polls is selection bias. The polls, though typically much larger than regular opinion polls, still sample only a small fraction of voters. In a heterogeneous population, sloppy selection of the sample can tilt results to any direction. This pitfall can be avoided if the polling organization is competent enough. However, there are problems more inherent to the nature of exit polls. Since the clients (the media) want to publicize results as soon as the real polls close, exit polls must close a few hours earlier. Therefore, late-hour voters are not sampled at all. Some constituents tend to vote early, for example the elderly and stay-at-home mothers, and are oversampled in the exit polls. Other constituents tend to vote late and are under-sampled. This may be the explanation for the 2004 US presidential election discrepancy between early exit polls indicating a Kerry victory, and the final outcome. Additionally, voters may be more or less willing to participate in the exit polls, or more or less willing to sabotage the poll by providing a false vote, depending on their political tendency. This is known as nonresponse and response bias, respectively."

Please explain why you removed this, User:Buon professore ImperatorExercitus (talk) 03:27, 21 October 2008 (UTC)

As i said above, there is not a citation in this section. I can find no evidence anywhere of this supposedly "famous example of exit poll error."

Everything else in the section is not only uncited, but false, and the kind of cant that's been used to ignore wide disparities that indicate fraud and ought to motivate investigations. —Preceding unsigned comment added by Buon professore (talkcontribs) 03:40, 21 October 2008 (UTC)

I've restored the mention of the 1992 UK election exit polls -- it is well known in polling circles as the canonical example of the failure of exit polls. It was a result of numerous small factors that combined to produce a significant bias in one direction that was magnified by the sensitivity of the electoral system to small changes in voting behaviour in a close election. Unfortunately much of the research into those exit polls is not available online. Duncan Keith (talk) 05:55, 23 October 2008 (UTC)


There's mention of the inventor. There's no mention of when he invented it (not even on his page, which does mention him doing it since 1963).

So, when was the first exit poll? What's the freakin' history?!

--jae (talk) 16:17, 28 January 2013 (UTC)