A Reply to Nate Silver’s “Ten Reasons Why You Should Ignore Exit Polls


Richard Charnin (TruthIsAll)


Oct. 29, 2010


Nate, this is a reply to your November 2008 post.  I realize it is two years after the fact, but with the midterm elections next week, I thought it would be instructive to review what you said about exit polls. I for one would like to know if you feel the same way about them. I’m still waiting for your response to these twenty-five questions I posed back in July. But after reading your “ten reasons”, I can come up with ten reasons why you have never responded. The “experts” whom you cite are anything but.


You begin with this: “Oh, let me count the ways. Almost all of this, by the way, is lifted from Mark Blumenthal's outstanding Exit Poll FAQ. For the long version, see over there”.


Your first mistake was to believe all those discredited GOP talking points. Now I will count the ways.

Are you asking us to ignore a) the final exit polls or b) the unadjusted, preliminary state and national exit polls? If it’s (a), then you must believe that election fraud is systemic since final exit polls are always forced to match the recorded vote, even if it is fraudulent. If it’s (b), then you must believe election fraud is a myth. Based on your sources, it must be (b) and you probably believe “voter fraud” is real.


1. 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.

RC: Not true, pure baloney. I should stop right here. Exit polls have a much smaller margin of error than pre-election polls. Perhaps you are unaware that exit pollsters Edison-Mitofsky state in the notes to the  National Exit Poll  as well as in the NEP Methods Statement  that exit poll respondents were randomly-selected and the overall margin of error was 1%. Adding a 30% cluster effect raises the calculated 0.86% MoE to 1.1%. It stands to reason that exit polls are more accurate than pre-election polls because a) those polled know exactly who they voted for and b) in pre-election polls, respondents might change their mind - or not vote. http://richardcharnin.com/TrueVoteModelDocGettingStarted.htm

 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.


RC: Of course the Democrats always do better in the exit polls than in the recorded vote. But did you ever consider why? Perhaps you are unaware that millions of votes are uncounted in every election? And that the vast majority are Democratic (over 50% are in minority districts)? The U.S. Census reported over 80 million net uncounted votes since 1968. You make the false assumption that the recorded vote is the True Vote. Uncounted votes alone put the lie to that argument, not to mention votes switched at the DREs and central tabulators. It is also contradicted by a linear regression analysis: non-response rates increased from the strongest Bush states to the strongest Kerry states, suggesting that non-responders were Kerry voters.

Read about it here: http://richardcharnin.com/StateExitPollDiscrepancies.htm


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


RC: You are apparently unaware of Rush Limbaugh’s “Operation Chaos” in which he advised Republicans to cross over in the Democratic primaries and vote for Hillary Clinton? His objective was to deny Obama the nomination.  Obama easily won the all the caucuses in  which voters were visually counted? Read about it here:  http://richardcharnin.com/2008PrimariesLinks.htm

 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.


RC: You are apparently unaware that exit pollsters Edison-Mitofsky wrote in the notes to the 2004 National Exit Poll that respondents are randomly selected as they exit the polling booth. What is your definition of a random sample?

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.


RC: You quote a biased GOP pollster who never did an exit poll. There is no evidence that Democrats are more likely to participate. In fact, 2004 exit poll data shows just the opposite.  You are resurrecting the reluctant Bush responder (rBr) hypothesis that was disproved by the exit pollster’s own data.


 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.


RC: You are apparently unaware that exit pollsters Edison-Mitofsky claimed that their 2004 precinct design sample was near perfect: http://www.ap.org/media/pdf/EvaluationEdisonMitofsky.pdf

You mention Florida 3000, but are either unaware or choose to ignore the fact that 180,000 spoiled punch card ballots were never counted - and 70% voted for Gore. Are you aware that GOP election officials discarded Democratic absentee ballots and included GOP ballots that were filed after the due date? Are you unaware of the Palm Beach butterfly ballot? Do you really believe that Bush won Florida in 2000? http://archive.democrats.com/display.cfm?id=181

 Exit polls may also miss late voters. By "late" voters I mean persons who come to their polling place in the last couple of hours of the day, after the exit polls are out of the field. Although there is no clear consensus about which types of voters tend to vote later rather than earlier, this adds another way in which the sample may be nonrandom, particularly in precincts with long lines or extended voting hours.


RC: You apparently are unaware that Kerry was leading the National Exit Poll by a steady 3-4% at 4:00pm (8649 respondents), at 7:30 pm (11027) and 12:22am (13047).   As a quant guru, you should ask how was it that Kerry led by 51-48% at 12:22 am but Bush led at the final (13660) after just 613 additional respondents? It’s simple. The pollsters had to force the National to match the bogus recorded vote (Bush 50.7-48.3%). It was impossible - a sham. The fact is that Kerry led the final unadjusted NEP 13660 by 51-47.5%.  Are you aware that final exit polls are always FORCED to match the recorded vote?  Read about the final 5 million recorded votes here: http://www.richardcharnin.com/Final5mRecordedVotes.htm,  


In 2008, Obama won the unadjusted National Exit Poll (17836 respondents) by 61-37%. But the poll was forced to match the recorded 52.9-45.6%vote.  Are you aware that Obama had 52.4% of 121 million votes recorded on Election Day and 59.2% of the 10 million late votes recorded  later?

 "Leaked" exit poll results may not be the genuine article. Sometimes, sources like Matt Drudge and Jim Geraghty have gotten their hands on the actual exit polls collected by the network pools. At other times, they may be reporting data from "first-wave" exit polls, which contain extremely small sample sizes and are not calibrated for their demographics. And at other places on the Internet (though likely not from Gergahty and Drudge, who actually have reasonably good track records), you may see numbers that are completely fabricated.


RC: You quote Matt Drudge of all people? Guess you were unaware of that  Kerry led by a steady 51-48% from 4pm (8349 respondents) to 12:22am (13047) to the final 13660. http://www.richardcharnin.com/MatchingFinalExitPollToTheVote.htm

 A high-turnout election may make demographic weighting difficult. Just as regular, telephone polls are having difficulty this cycle estimating turnout demographics -- will younger voters and minorities show up in greater numbers? -- the same challenges await exit pollsters. Remember, an exit poll is not a definitive record of what happened at the polling place; it is at best a random sampling.


RC: Perhaps you are unaware that the National Exit Poll indicates that Kerry won 57-62% of new voters. And that Obama had 72% of new voters in 2008. But you now agree that exit polls are indeed random samples. Glad you corrected point # 4. Obama had 72% of new voters in 2008.


 You'll know the actual results soon enough anyway. Have patience, my friends, and consider yourselves lucky: in France, it is illegal to conduct a poll of any kind within 48 hours of the election. But exit polls are really more trouble than they're worth, at least as a predictive tool. An independent panel created by CNN in the wake of the Florida disaster in 2000 recommended that the network completely ignore exit polls when calling particular states. I suggest that you do the same.


RC: Exit polls are more trouble than they are worth? Yes, it’s true - for those who rig the elections. Perhaps you are unaware that the exit polls were the first indicators that the 2004 election was stolen. Nate, your problem is that you refuse to admit that Election Fraud is systemic - or that it even exists. You want your readers to believe that the recorded vote accurately depicts true voter intent and that the exit polls are always wrong. Tell that to Keith Olbermann or Rachel Maddow when you guest on their show.


You are probably unaware that the unadjusted 2008 exit polls confirm that Obama won by 23 million votes with a 58% share – not by the bogus recorded 9.5 million and 52.9% share. Obama won the 58% True Vote share using the identical final National Exit Poll vote shares – but with a feasible returning voter mix replacing the impossible Final NEP mix which was required to force the poll to match the recorded vote. Read about it here: http://richardcharnin.com/ObamaProof.htm


You would agree that 103% turnout of living 2004 Bush voter is impossible, yes? And also agree that the NEP inflated the number of returning 2004 third-party voters by indicating there were 5 million even though 1.2 million were recorded? And that there could not have been 12 million more returning Bush voters than Kerry voters – especially since Bush won the recorded vote by 3 million and Kerry won the True Vote by 10 million? http://richardcharnin.com/FurtherConfirmationOfaKerryLandslide.htm


We have the 1988-2008 unadjusted numbers from the Roper website. It shows that Obama had 61% in the National Exit Poll (17,836 respondents) and 58.0% in the state exit poll aggregate – exactly matching the True Vote Model. The Democrats led by 52-42%; but just 48-46% in the recorded vote. That’s an awful lot of Reluctant Republican Responders, yes?



You are probably unaware that of the 274 state exit polls in the 1988-2008 presidential elections, 126 exceeded the margin of error (including a 30% cluster factor). Only 14 would be expected to exceed the MoE at the 95% confidence level. Of the 126, 123 “red-shifted:” to the Republican and THREE to the Democrat. The probability is 5E-106. Can you explain it?

P= 0.0000000000 0000000000 0000000000 0000000000 0000000000 0000000000 0000000000 000000000 00000000000 0000000000 000005

Read about it here: http://richardcharnin.wordpress.com/category/election-myths/


Finally, Nate, take a look at this. You need a real education on exit polls.