538's Nate Silver-Ten Reasons Why You Should Ignore Exit Polls

[DemocratSinceBirth]

Exit polls have a much larger intrinsic margin for error than regular polls. This is because of what are known as cluster sampling techniques. Exit polls are not conducted at all precincts, but only at some fraction thereof. Although these precincts are selected at random and are supposed to be reflective of their states as a whole, this introduces another opportunity for error to occur (say, for instance, that a particular precinct has been canvassed especially heavily by one of the campaigns). This makes the margins for error somewhere between 50-90% higher than they would be for comparable telephone surveys.

2. Exit polls have consistently overstated the Democratic share of the vote. Many of you will recall this happening in 2004, when leaked exit polls suggested that John Kerry would have a much better day than he actually had. But this phenomenon was hardly unique to 2004. In 2000, for instance, exit polls had Al Gore winning states like Alabama and Georgia (!). If you go back and watch The War Room, you'll find George Stephanopolous and James Carville gloating over exit polls showing Bill Clinton winning states like Indiana and Texas, which of course he did not win.

3. Exit polls were particularly bad in this year's primaries. They overstated Barack Obama's performance by an average of about 7 points.

4. Exit polls challenge the definition of a random sample. Although the exit polls have theoretically established procedures to collect a random sample -- essentially, having the interviewer approach every nth person who leaves the polling place -- in practice this is hard to execute at a busy polling place, particularly when the pollster may be standing many yards away from the polling place itself because of electioneering laws.

5. Democrats may be more likely to participate in exit polls. Related to items #1 and #4 above, Scott Rasmussen has found that Democrats supporters are more likely to agree to participate in exit polls, probably because they are more enthusiastic about this election.

6. Exit polls may have problems calibrating results from early voting. Contrary to the conventional wisdom, exit polls will attempt account for people who voted before election day in most (although not all) states by means of a random telephone sample of such voters. However, this requires the polling firms to guess at the ratio of early voters to regular ones, and sometimes they do not guess correctly. In Florida in 2000, for instance, there was a significant underestimation of the absentee vote, which that year was a substantially Republican vote, leading to an overestimation of Al Gore's share of the vote, and contributing to the infamous miscall of the state.


More...



http://www.fivethirtyeight.com/




OH EDIT -THIS IS NOT MY ANALYSIS...I READILY ADMIT WHEN THINGS ARE BEYOND MY KEN...IF YOU DON'T LIKE MR. SILVER'S ANALYSIS PLEASE DIRECT YOUR COMMENTS TO <[e-mail]>

THANK YOU.

[WI_DEM]

1. agreed don't put much stock in leaked exit polls even if they are good for Obama.

[BeFree]

2. Miscall of the state?!?!

BULLSHIT. They called Florida correctly. Gore won.

So who can believe the rest of that BS? Not me. All of it stinks.

[DemocratSinceBirth]

3. I Believe Gore Won Too But Not By Not Enough To Justify The Early Call

~

[BeFree]

5. Beliefs are like.... everybody's got at least one.

The hand-counts, not including the butterfly fiasco and the million or so invalidated votes, showed a narrow win for Gore. But put all the evidence together and there was no miscall. Now, if you ignore most evidence it is possible to come up with an op like your's. And hold such beliefs.

[Marsala]

7. Even if Florida went for Gore, they still called it too early

It was way too close for an early call. They called it for Bush later on and that got reversed, too.

The point is that exit polls aren't trustworthy.

[DemocratSinceBirth]

8. They Prematurely Called Florida For Senator Buddy McKay In 1988

~

[BeFree]

14. Bullshit

It was not to early. I am sick of people trying to re-write history. The exit-poll call was proven to be the correct call. Gore really won Florida!! So the exit-poll had it right.

The point is that you don't have much of a clue of the exit-polls. Check out the DU election reform archives and see that I sure as hell do.

[LiberteToujours]

17. It was too early

Regardless of the fact that Gore got more votes in Florida, the margin of victory was too narrow for the prediction of victory by the exit polls to have been anything more than chance. The margin of error of the exit polls was much larger than the margin by which Gore won the state.

[BeFree]

19. What was the margin, in your book?

My book says Gore won by about 300,000 votes.

Add up all the butterfly, lost, destroyed and mismarked ballots, Gore won handily, and the exit-polls called it.

[keepthemhonest]

4. I think you are missing point number one ...stolen elections

in 2000 and 2004.That would explain perfectly why the exit polls don't match up.Do you remember THRUTHISALL and all of the calculations that poster would do showing the impropabilities of all of those polls being off?It showed Bush had a better chance of winning the lottery than having all those exit polls be so off in his favor.

[Marsala]

9. Did you read the whole post?

"In 2000, for instance, exit polls had Al Gore winning states like Alabama and Georgia (!). " Do you think that Gore actually won those states? In 2004, the exit polls were way off in states like New York and Utah. Were the Republicans stealing New York and Utah by up to five percent? Of course not.

Exit polls suck.

[keepthemhonest]

12. Do you think Bush won florida in 2004?

simple question for you and then go read all of those reports.

[Overseas]

10. I agree. Maybe Nate is debunking them for hour by hour info on who is in the lead.

I don't think he was talking about using exit polling to compare with vote totals, as we do to determine the fairness of elections around the world.

That's the only reason I can see for Nate telling people not to follow them.

Because in 2004, the exit polling tracked the vote totals in Ohio, 51 Kerry, 48 Bush until after 11 pm when the VOTE TOTALS DIVERGED SIX POINTS -- Kerry down three, Bush up three. That would have been a red flag in evaluating an election in another country. In ours, the exit polls were adjusted to match the vote counts even though they'd been tracking very closely until that point.

And then there were immediate TV pundit discussions about how exit polls can be faulty. Lots of discussion of faults in exit polls. No discussion of how rare it is to have a SIX POINT DIVERGENCE between exit polling and vote totals, especially with the world renowned firms.

www.stealingamericathemovie.org for a free documentary with footage and lots of sources of data from that evening and other traumatic evenings.

[DemocratSinceBirth]

11. You Are 100% Right...He's Referring To Raw Exit Polls

And exit polls are good checks on the actual results as a check agaiost fraud with one caveat...Even exit polls have a margin of error so their utility is reduced in a 50/50 election like 00...

[keepthemhonest]

18. oh I see thanks

I just have been hearing a bunch of people on the news( and o/w) say ignore the exit polls.I fear it is so they can cheat and say Mccain won.That is whre I am coming from

[keepthemhonest]

6. did you now see the Berkely report

showing the impropability of bush winning.

What about Stephen Freeman from university of Pa

or this http://www.uscountvotes.org/ucvAnalysis/US/USCountVotes_Re_Mitofsky-Edison.pdf


This has gone essentially ignored...

[Drunken Irishman]

13. I don't buy the exit polls had Gore winning Alabama and Georgia.

Those states were called for Bush shortly after polls closed. If the exit polls had Gore winning, they would not have made a projection that quickly, it just would not have happened.

[mhatrw]

15. Exit polls are notoriously bad at predicting stolen election results! n/t

[progressivebydesign]

16. Exit polls were SPOT ON until 2000. It's not the polls it's the COUNTING. n/t