The Exit Poll Disparity: Mystery Solved!

Brad Friedman

January 19, 2005, 11:34am
PT

77 Comments

Well, now we get a whole new story about what was “wrong” with the Exit Polls on November 2nd.

As you may recall, the original explanation for the disparity between the Exit Poll results and the Final Results was attributed to the theory that pollsters oversampled female voters. The results at the time, were therefore re-weighted to reflect that theory.

But today, according to CNN’s report on a new “internal review” by the Exit Polling Consortium, we find that it was actually due to the fact that “more Kerry supporters participated in the survey than Bush voters”.

In other words, had only more voters told the Exit Pollsters they had voted for Bush, the Exit Polls would have matched the Final Results.

In other words, there continues to be no explanation for the Exit Polls not matching the Final Results.

Quoting from CNN’s report on the report:

Exit polls overstated John Kerry’s share of the vote on November 2, both nationally and in many states, because more Kerry supporters participated in the survey than Bush voters, according to an internal review of the exit-polling process released Wednesday.

The report said it is difficult to pinpoint precisely why, in general, Kerry voters were more likely to participate in the exit poll than were Bush voters. “There were certainly motivational factors that are impossible to quantify,” the report said.

Could it be that Kerry voters were more likely to paricipate in the exit poll because there were more Kerry voters than Bush voters? The report, apparently, would like you to not believe that could be the case.

In other words, there continues to be no explanation for the Exit Polls not matching the Final Results.

But lest we determine that there is any reason to be skeptical of CNN’s analysis of the report, let’s take a look at this graf:

CNN did not air those inaccurate results or post them on its Web site, and CNN’s projections of winners on election night were accurate.

That, of course, is true.

Unless you look at actual evidence which shows they are lying. (While you’re there, please notice in the two CNN.com screenshots how the Male/Female support for Bush/Kerry changed from one screenshot to the next posted just an hour and twenty minutes later with only 57 new respondents added to a poll of 2,020 respondents. Please also note that the percentage of Male vs. Female respondents stayed consistent over both screenshots at 47%/53%.)

But such unexplained phenomon simply didn’t occur according to CNN, so it must be beside the point.

So if the problem was not oversampling of Female voters, what exactly was the problem that leads the consortium to instruct us that the Exit Polls were wrong but the Final Results were right?

CNN’s report on the report seems to indicate that there is no reason. Above and beyond the fact that more Kerry voters said they voted for Kerry than Bush voters who said they voted for Bush.

And apparently this occurred — by a complete freak of nature — in 26 of 30 states polled:

The new report shows that exit polls overstated Kerry’s support in 26 states, while estimates overstated Bush’s support in four states.

Clear on all of this yet?

If not, CNN has neatly identified a few more helpful factors to look at:

The report identified several factors that may have contributed to the discrepancy, including:

Distance restrictions from polling places imposed upon the interviewers by election officials at the state and local level. {ed. note: Bush voters shot straight up out of the polling place and down into their car, unlike Kerry voters who walked by the pollsters as they crossed the long distance from the poll to their cars}

Weather conditions, which lowered completion rates at certain polling locations. {ed. note: It rained more on the top of Bush voters heads than on the top of Kerry voters at the same polling locations.}

Multiple precincts voting at the same location as the precinct in the exit poll sample. {ed. note: We have no clue what this would have to do with anything, and can’t come up with a joke to make it more absurd than it already sounds.}

Interviewer characteristics, such as age, which were more often related to the errors last year than in past elections. {ed. note: Bush voters don’t like talking to younger people. Or, they don’t like talking to older people. Whereas Kerry voters, not that there were more of them, will talk to anybody. Or they’re making all this bullshit up outta whole cloth.}

Well, I’m glad that’s all settled.

UPDATE: MSNBC continues the whitewash, declaring “Exit polls say Bush won fair and square: Report on surveys finds system worked, even with errors”. Though their article similarly gives no explanation for what happened…other than saying it happened. Sometimes a headline is enough to sell the messaage apparently.

77 Comments

Categories: (Uncategorized)

Reader Comments on