« Some non-election news, Part I | Main | Some non-election news, Part II »

Republicans Beware of Exit Polls

The RNC at GOP.com has a long post detailing why Republicans should be wary of exit polls:

  • Election Experts Believe Exit Polls Give An Edge And Sway Towards Democrat Candidates.
  • National Exit Polls Will Skew In Favor Of Democrats This Year, Due To Large Numbers Of Uncontested Democrat Seats In The House Of Representatives.
  • Early Exit Polling Returns In 2004 Were Widely Inaccurate, Declaring Sen. John Kerry (D-MA) To Be The Next President Of The United States And Republicans Barely Holding A One Seat Majority In The U.S. Senate.
  • In The 2002 Midterm Elections, Exit Polling Produced Unusable Data.
  • In 2000, Exit Polling Malfunctioned And Incorrectly Projecting Vice President Al Gore As The Winner Of The Crucial Battleground State Of Florida.

Read the entire piece because it includes a lot of statistics from past elections illustrating how unreliable and deceptive past exit polls were.


Comments (21)

National Exit Poll... (Below threshold)
langtry:
National Exit Polls Will Skew In Favor Of Democrats This Year, Due To Large Numbers Of Uncontested Democrat Seats In The House Of Representatives. ggsactly. Makes a whole lot of sense to poll people leaving polling places in Chicago, New York City, Boston or San Francisco and then extrapolate it into a crosscountry landslide. Asshats.
Democrats lie. It's not n... (Below threshold)
theExecutioner:

Democrats lie. It's not news anymore. It's common knowledge.

I am still pouting over Dan... (Below threshold)
Mitchell:

I am still pouting over Danny Ortega's probable win in Nicaragua. It's bad enough that the Dims. have a shot here.

F Ortega. And F the Dim. Party.

Go GOP!

Looks like the RNC knows th... (Below threshold)
Lee:

Looks like the RNC knows that the GOP is on for a royal *ss kicking today. Whooyah!

Mitchell, remember when you... (Below threshold)
BarneyG2000:

Mitchell, remember when you wrote this?

Right now I would not bet on Ortega. He always polls high (hell, he's been defeated 3 times since 1990) and ends up losing. A Brown and Harvard educated guy will most likely win. And vindicate our decision to stand with the people, not the dicsredited socialist ideal, in Nicaragua.

So just fuck right off. Posted by: Mitchell

So, who should F-Off now?

Democrats lie. It's not ... (Below threshold)
Brian:

Democrats lie. It's not news anymore. It's common knowledge.

If Democrats lie, that means they tell exit pollsters that they voted Republican, which means the exit polls would skew Republican, which is the opposite of this article.

You should at least try to appear rational.

Brian, Your incred... (Below threshold)
politicals:

Brian,

Your incredible intellect is on display. Now what if a democrat told the pollster they were a republican or independent, but voted democrat. No wonder you are a democrat - you really can only see things in one skewed way!

Lee,Please unplug ... (Below threshold)
politicals:

Lee,

Please unplug your keyboard - there is no available bandwidth for your illogical postings today. Now please, just follow the instructions and the world (and this blog) will be a better place.

What party a Dem tells a po... (Below threshold)
Brian:

What party a Dem tells a pollster they belong to is irrelevant. All that matters is what they report as their vote. My incredible intellect trumps your lousy logic here.

No wonder you are a Republican. Even when there are just two choices, "truth" or "lie", you still struggle to find a way it can be "skewed".

I suggest you refrain from criticizing the intellect or logic of other posters today. You're only making yourself look foolish and desperate.

Brian,Or, rather, ma... (Below threshold)
SCSIwuzzy:

Brian,
Or, rather, maybe a sizeable handful of exit pollsters (volunteers) aren't entirely honest.

We saw in RR's landslide that people stayed home and didn't vote when the exit polls and east coast returns convinced them that things were already decided.
Winning elections in today's atmosphere is about getting your base motivated to vote and convincing the opposition that they have already lost and should stay home.

Brian,Polls 101 te... (Below threshold)
politicals:

Brian,

Polls 101 teaches that any poll must reflect the proportionate number of identified republicans, dems or independents in an area to get a proper statistical sampling. A random sample as you suggest would be completely meaningless and should never be reported.

Later in polls 101 you can consider how misidentifying ones party would skew the polls that were trying to properly reflect the voter demographics.

"pucker puss" (lee lee)-so?... (Below threshold)
jhow66:

"pucker puss" (lee lee)-so? one word VETO--he he

Polls 101 teaches that a... (Below threshold)
Brian:

Polls 101 teaches that any poll must reflect the proportionate number of identified republicans, dems or independents in an area to get a proper statistical sampling.

Sorry, that's wrong. Statistics teaches that any poll must be done on a purely random sample of the population (admittedly hard to do), without regard to political affiliation. A poll that actively seeks out x% of Dems and y% of Reps is meaningless.

To clarify, "meaningless" a... (Below threshold)
Brian:

To clarify, "meaningless" as a source for generalizing to the full population. It's certainly legit to report on responses within those smaller populations, though.

Sorry, that's wrong. Sta... (Below threshold)
Dan:

Sorry, that's wrong. Statistics teaches that any poll must be done on a purely random sample of the population (admittedly hard to do), without regard to political affiliation. A poll that actively seeks out x% of Dems and y% of Reps is meaningless.

The catch is in that phrase "admittedly hard to do". If you don't check the internals of your polling, your results are, as you say, meaningless. If your attempt at randomly sampling a group of voters ends up (even unintentionally) sampling 2:1 in the favor of one party, your results will be horribly wrong. Thus polling companies monitor their internals and adjust their predictions accordingly.

As for the original post, it's interesting to note that (as far as I can tell) there haven't been any leaks yet. Instapundit thinks that is good news for Republicans, which I comment about here.

"one word VETO--he he"</... (Below threshold)
Lee:

"one word VETO--he he"

Yeah, he he, repeated vetos by Bush will insure a Democratic is elected to the White House in '08, he he... you moron.

If your attempt at rando... (Below threshold)
Brian:

If your attempt at randomly sampling a group of voters ends up (even unintentionally) sampling 2:1 in the favor of one party, your results will be horribly wrong.

That's why there are formulas for determining the appropriate sample size that manage the likelihood of things like that happening, and take them into account in the analysis. If your sample size is large enough, you don't need to worry about unintentional skewing.

Barney, you might recall my... (Below threshold)
Mitchell:

Barney, you might recall my post was in response to yours telling us all that Danny Ortega was President, about a week before the elections had been held.

And, do you realize that he only won because his corrupt party, in tandem with the corrupt conservative party, lowered the threshold for winning in the first round to 35%.

So, about 62% of Nicaraguans, at latest count, have voted against your Commandante Ortega.

You really are a piece. Well, you know the rest of that phrase.

Hey "pucker puss" (lee lee)... (Below threshold)
jhow66:

Hey "pucker puss" (lee lee) want to bet? The people will see how Bush protected them from your asskissing, bootlicking, appeasing liberals that want to turn the USA into a socialist nation. Makes no differance if your side does come out a few winners as you still will not have enough to override a VETO. Stick that up your whimpy ass. Bring it on! (where have I heard that?)he he

jhow66-moron (defination of moron-one who gets under the skin of "pucker puss" (lee lee)-formanally know as just plain old "lee") snicker snicker (not the candy bar)-pertaining to LOL

Cry me a river Mitchell. Y... (Below threshold)
BarneyG2000:

Cry me a river Mitchell. You were wrong, and you made a fool of yourself. Got any more excuses?

That's why there are for... (Below threshold)
Dan:

That's why there are formulas for determining the appropriate sample size that manage the likelihood of things like that happening, and take them into account in the analysis. If your sample size is large enough, you don't need to worry about unintentional skewing.

Well sample size is not enough; the hard part is the truly random. Let's say you tell me sampling 1000 people is enough to be a representative sample for a local population. If I go and sample 1000 people outside a coffee house in a downtown area, I will get much different results than if I sample 1000 people as they leave a local church.

This is actually my problem with most modern polling. There are so many cases of skewed sampling (even with a significant sample size) that the poll results are just an indication of the skew, and have little bearing on the population as a whole.




Advertisements









rightads.gif

beltwaybloggers.gif

insiderslogo.jpg

mba_blue.gif

Follow Wizbang

Follow Wizbang on FacebookFollow Wizbang on TwitterSubscribe to Wizbang feedWizbang Mobile

Contact

Send e-mail tips to us:

[email protected]

Fresh Links

Credits

Section Editor: Maggie Whitton

Editors: Jay Tea, Lorie Byrd, Kim Priestap, DJ Drummond, Michael Laprarie, Baron Von Ottomatic, Shawn Mallow, Rick, Dan Karipides, Michael Avitablile, Charlie Quidnunc, Steve Schippert

Emeritus: Paul, Mary Katherine Ham, Jim Addison, Alexander K. McClure, Cassy Fiano, Bill Jempty, John Stansbury, Rob Port

In Memorium: HughS

All original content copyright © 2003-2010 by Wizbang®, LLC. All rights reserved. Wizbang® is a registered service mark.

Powered by Movable Type Pro 4.361

Hosting by ServInt

Ratings on this site are powered by the Ajax Ratings Pro plugin for Movable Type.

Search on this site is powered by the FastSearch plugin for Movable Type.

Blogrolls on this site are powered by the MT-Blogroll.

Temporary site design is based on Cutline and Cutline for MT. Graphics by Apothegm Designs.

Author Login



Terms Of Service

DCMA Compliance Notice

Privacy Policy