« Religion and the 2004 Election | Main | What Mandate? »

A Tour of the 2004 Exit Poll: What It Says and What It Doesn't

Here are some observations on the 2004 exit poll data, based on the latest version of the data available. There is much to be explained and understood about these data and certainly legitimate questions can be raised about some of the findings. But the first task is simply to clarify what the poll actually says and does not say, because there is considerable confusion about this.

The figures used here are not the final figures, but, based on my experience in previous election cycles, they probably vary only slightly from the final numbers available when the exit poll authorities (in this case, the National Election Pool (NEP)) release a cleaned-up dataset in a couple of months with final weights.

All 2004 figures discussed here refer to the NEP exit poll not the Los Angeles Times exit poll, since the NEP poll is both substantially larger and far and away the most widely-used and cited. All 2000 figures refer to the 2000 exit poll by VNS, the NEP's predecessor.

1. Gender. According to the NEP poll, Bush carried men by 11 points (55-44), exactly the same margin he had in 2000 when he carried men by 53-42. Among women, however, Kerry's margin was only 3 points (51-48), down from the 11 point margin Gore had in 2000 (54-43). No matter how you measure the gender gap (add the margins and divide by 2 or simply subtract Democratic male support from Democratic female support), this means a substantial compression of the gender gap (from 11 or 12 points, down to 7) and it is entirely due to the Democrats' reduced margin among women.

2. Race. According to the NEP poll, 23 percent of voters this year were minorites, up from 19 percent in 2000, indicating the continued rapid expansion of the minority electorate.

The NEP poll says, however, that Bush widened his margin among white voters--still 77 percent of voters--to 17 points (58-41), up from a 12 point margin (54-42) in 2000. And among hispanics, now 8 percent of voters, the poll indicates a Kerry margin of only 53-44, a dramatic compression from Gore's 62-35 margin among the same group in 2000.

However, there is some dispute about whether the compression of the Democratic margin was as severe as indicated by this poll. An exit poll of Hispanics only by the William C. Velásquez Institute of San Antonio, which sampled 54 counties in the 14 states with the largest number of Latino registered voters, had 68 percent voting for Kerry and only 31 percent voting for Bush.

To further sow confusion, the NEP data on hispanics are now being reported in two different ways--as above, at 8 percent of voters and 53-44 Democratic support and at 6 percent of voters and 56-43 Democratic support in Sunday's New York Times. How did hispanics suddenly get demoted to 6 percent of voters? The answer is complicated, but here it is: the NYT for purposes of their historical chart uses a single race question to capture hispanics, as opposed to a race question plus another question on whether the respondent is of hispanic descent or not, which was included on both the 2000 and 2004 exit polls and is now used by CNN and practically everyone else. The NYT's reasoning for not using this new (and better) two question measure of hispanic respondents is that the historical hispanic data in their chart will at least all be measured in the same way.

I certainly see the point in apples-to-apples comparisons. On the other hand, since the new measure is undoubtedly a better one and we don't really believe the hispanic proportion of voters in 2000 was only 4 percent (as the single question hispanic series also indicates) and just 6 percent this year, it would be better, I think--as well as less confusing--for the NYT to go with the data that is the best and simply acknowledge a discontinuity in the exit poll times time series on hispanics between 1996 and 2000.

People will, after all, play the closest attention to the figures--both support rates and proportion of voters--from this year and, secondarily from 2000. Given that the figures from the two question hispanic measure for those two years are (a) better and (b) comparable with one another, it strikes me as a good idea to feature those data rather than the misleading single question hispanic data. Again, the discontinuity can then be footnoted for those that get into the data that far, but the average NYT reader will be provided with the most accurate measure of hispanic turnout and presidential support.

The data on blacks are much more straightforward. Among blacks, Kerry had an 88-11 margin, down only slightly from 2000's 90-9 margin for Gore. In fact, except for 2000 and Mondale's 1984 campaign, Kerry's margin among blacks is the highest obtained by a Democratic candidate since the exit polls started in 1976.

More exit poll fun tomorrow!



Was there voter fraud in Florida in this election? Ruy, information from Democratic Underground is quite frightening. They are claiming that 100,000 more Republicans than were registered to vote voted via optical scanning in Florida in counties that used optical scanning.

They are claiming 105 percent turnout for Republicans in optical scanning counties and 98 percent turnout statewide based on actual polling data from Florida. If this is true this is prima facie fraud! This would have to be the political scandal of the century if not the entire history of the American Republic.

If true, it would also call into question the voting results of many other states in America which used the same voting machines and, in particular, would call into question the results in Ohio.

Could you please, please look into this and respond. If these claims are baseless it would help for you to explain why. If they are true your voice could be quite important in exposing one of the greatest if not the greatest political scandal in American history.

Personally, I find this data hard to believe but it seems quite straightforward and quite shocking as well.

Karl Rove is indeed brilliant. I recall some measure in California on the gay issue a couple of years ago that hispanics turned against in large numbers. It looks like Karl used the gay marriage issue to lure them in.

The increased vote among women, I can't explain.

The challenges over whether or not the election was a fraud are still moving forward, but if you're data's right they won't go anywhere.

America really has become unhinged.

Understanding why this group or that group voted for Bush is certainly going to help Democrats win future elections. Not by abandoning traditional Democratic principles, but by communicating traditional Democratic principles more effectively.

Yet, we should not focus too much on reaching different groups in different ways. We have a bigger problem, and it's how we reach Americans - as a WHOLE.

Republicans have been winning because they effectively communicate the idea that they LIKE all of their fellow Americans - except for some tiny power elites. Whereas many Democrats - at least at the grassroots level - have been effectively communicating the idea that they DISLIKE huge chunks of the population: the rural, the religious, and the less educated. Just one week ago, you could have gone to the official Kerry-Edwards site and seen plenty of evidence of this. (Not from the campaign, but in the discussion forum.) I certainly found evidence of anti-rural feeling, anti-religious feeling, and educational snobbery at the local Kerry-Edwards headquarters.

It just might be time to invite the Far Left out of the coalition. They are doing the Party far more harm than good.

Please do more detailed analysis of why the exit polling was so screwy this year. Even mystery pollster says the NEP results were misleading. It is because the late afternoon data was so far off the mark that the internet is aflame with 'analysis' proving skullduggery and fraud.
Analyzing the almost final data is important, but what happened in the late afternoon? Why were so many of the media telegraphing a Kerry win? How did NEP get this so wrong? Help us understand.


Just in case people don't think there was any voting fraud.

It is time for the DLC to go. A real republican will beat a faux republican every time. You might say that Bill Clinton won by adhering to DLC principles and I would counter with the fact that we are fresh out of Bill Clintons.

Has anyone seem this article and do you have any backup information. http://www.michaelmoore.com/words/index.php?id=284

I'm not one to quote the often noxious Michelle Malkin, but she does go through the numbers on Hispanics from the exit polls in this post on her blog:


I hope that Ruy and other will read this take and give us some analysis of the arguments about whether the NEP data will come to be regarded as unreliable? Thank you.

One question I have been wondering about is the "right track/wrong track" numbers and Bush's reelection.

We all assumed that "wrong track" is a criticism of Bush, but is it possible that some respondents answered "wrong track" thinking of gay marriage, sex on television and various other "morals" issues and voted for Bush as the person to put us back on the right (more conservative) track?

I too am alarmed by the allegations of fraud mentioned by M. Schaefer above. I would love to hear what EMD has to say about this data.

I don't agree with Tom's comments, but do agree that the Republicans do a MUCH better job of marketing their ideas. I utterly reject that there is anything wrong with the ideas of the left, but feel we haven't communicated them well. The fact that a majority of our country voted for Republican ideas doesn'tmake them right, nor does it overshadow the fact that they are tragically out of step with the rest of the globe. For Dems to succeed we need to be meaner, tougher and lie a lot more than we've done in the past. I say that not entirely as a joke. We need to popularize and sell our ideas a lot better than we've been doing, and by that I mean we need to reach back down to our American roots.

No matter how we cut it we got our asses handed to us by a smarter, more ruthless, more lethal and more primitive campaign.

Simplicity. Simple slogans, simple black and white ideas and a rejection of issues, intellect and moderation killed us.

The exit poll data shows Bush won a higher percentage of hispani votes than he did last time. Is this just a Bush phenomonon or did Hispanics vote at a higher percentage for other republicans as well?


In my opinion there are enough serious allegations of voter fraud both nationwide and in individual states to warrant further inquiry. But before requesting actual recounts and examination of voting machines and tabulators I have another suggestion.

I propose that some of the pollsters conduct post vote surveys to verify the election results nationwide and in various states such as Ohio and Florida and New Hampshire where serious claims of potential voter fraud have been made.

It seems only prudent to me to make sure that the vote results are correct and post election surveys of voters would be a relatively easy way to accomplish this. I would also suggest that the sampling be large enough in each of the surveys to keep the margin of error below + or - 1 percent so that if any major discrepancies are discovered the sampling error cannot be blamed for the result.

I do not believe the National Election Pool exit poll results should stand by themselves as definitive evidence of voting results. Michael Keefer in his article "The November 2 Exit Poll Scam" has raised serious concerns about the veracity of this data and separate post election surveys would go a long way towards proving or disproving his allegations.

Special Note: It looks like my earlier comment about the Florida voting result may be wrong. It looks like the blogger at Democratic Underground who purported to get more Republican votes in optical scan counties than registered Republican voters failed to factor independent voters into his calculations. The results in Florida still look suspicious but there is no prima facie case of fraud as I stated earlier. My apologies for making this earlier comment without fully examining the evidence.

Are there publicly available crosstabs somewhere?

I'm not sure whether or not the accusations of election fraud will pan out or not, but there's an important distinction to be made in comparing the exit polls to the final result. The final exit polls that we now have in hand include the actual voting machine tallies from each precinct. Therefore, if there is any fraud, these final numbers will be useless in exposing it, since they by definition would include the tainted tallies.

The only exit poll numbers that could conceivably be used to double-chek against fraud are those released just after the polls close -- they include weighting by the turnout at each precinct, but don't include the actual vote tallies themselves.

An interesting question -- are these intermediate exit poll results preserved anywhere?

What's the margin of error on all these figures? For example, could Bush's 9 pt increase among Hispanics be sampling error?

The smoking gun.


Take a look at the discrepencies with the different kinds of voting systems in Florida. Note the differences in percentages of expected votes and actual results on the op-scan systems which was not present on the touchscreen systems. Also note the manufacturer of the op-scan systems.

Nationally people voted 90% along party lines according to a CNN survey.
Could this explain the exit polls? I don't want to sound like a conspiracy nut but these results are very troubling and I'm cannot think of a reasonable explanation.

Mara: Is this the approach you're suggesting? "Hi - we on the Left don't like you rural, religious, less educated types very much, but look: we have better ideas than the Right!"

It wasn't ONE SINGLE allegation of fraud that is at issue, but a HUGE pattern across a number of states. Obviously it is being ignored by the people who run this website, which is a serious shame, as it is something on which they should have at least SOME expertise! This issue needs to be aggressively pursued, organized around, and brought into court. No point waiting for Kerry & the DLC Dems -- they along with the mass media simply let the Repubs win anyway, as I have been saying for WEEKS. This needs to be pursued even with their resistance and occasional support. Pressure Ruy, pressure lawyers and civil rights groups and the mainstream media AND FAST!