Take it for what it is:
In criticizing our polls, some people have suggested that Gallup is intentionally biased -- either pro-Bush or pro-Kerry, too conservative or too liberal, too much in favor of either Democrats or Republicans. The criticisms appear to depend on whether our polls at the time show more support for one candidate or the other, particularly in comparison with other polls at the time. Here are some points to keep in mind.
1. Our goal is to be as objective as possible in the conduct of our polls, so that we can present as accurate a picture as possible of what the public is thinking.
2. There is absolutely no incentive for Gallup to be biased in any direction. Ultimately, on Election Day, we want our numbers to correspond as closely to the final outcome as possible. It would do us no good to show a 13-point lead for one candidate, while in fact the other candidate wins.
3. Gallup's accuracy record over the years has shown no systematic bias toward either the Republican or the Democratic candidates. In the 17 presidential elections that Gallup has covered, there have been 8 in which the final prediction (compared with the actual election results) gave the Republican candidate slightly too large of a margin, 6 in which the Democratic candidate was given slightly too large of a margin, and 3 elections in which the margin was precisely accurate.
Since 1968, Gallup has shown a slightly too high margin for Republicans in three elections, slightly too high a margin for Democrats in three elections, and two elections with an exact prediction of the margin.
Here is how the accuracy record looks for the past several elections (the percentage in the difference between what the vote winner got and what Gallup showed):
2000: 2 points (error in Republican direction)
1996: 3 points (error in Democratic direction)
1992: 6 points (error in Democratic direction)
1988: 2 points (error in Republican direction)
1984: 0 points (exact prediction)
1980: 4 points (error in Democratic direction)
1976: 2 points (error in Republican direction)
1972: 0 points (exact prediction)
1968: exact prediction of the margin; Nixon and Humphrey's totals each underestimated by 1 point
1964: 3 points (error in the Democratic direction)
1960: 1 point (error in the Democratic direction)
1956: 2 points (error in the Republican direction)
1952: 4 points (error in the Democratic direction)
1948: 5 points (error in the Republican direction)
1944: 2 points (error in the Republican direction)
1940: 3 points (error in the Republican direction)
1936: 7 points (error in the Republican direction)
-------------------------------------
We've had many inquiries and comments about the latest Gallup Poll trial heat results on the presidential race. Our editorial team will be responding to as many of the issues raised as possible here over the next day or two.
One question that comes up frequently (and apparently is based on various statements bouncing around the Net) concerns the party identification of the respondents in our sample. The supposition on the part of some is that these party identification figures from poll to poll should be constant and the same as some standard established from previous polling.
That's simply not the correct way to look at party identification. At Gallup (as is the case for many other polling firms), we ask party identification at the end of the survey using this wording: " In politics, as of today, do you consider yourself a Republican, a Democrat, or an independent? " Our experience tells us that this is not a fixed demographic measure (like age or gender or ethnicity), but rather is a variable in and of itself. While many Americans are hard-core Republicans or hard-core Democrats and never would call themselves anything different, there is a group of Americans who have no firm party allegiance and whose political identification can and does shift during an election season.
In fact, if one candidate is doing particularly well, it is usually the case that more people in the sample will identify with that candidate's party. Thus, if Kerry is having a good period of time in the campaign (as was the case after the Democratic primaries last February and March, and again in June and July of this summer), then more people will identify as Democrats at the end of the questionnaire when we ask with which party they identify "as of today." If Bush is doing better, as he is now, then more people at the end of the questionnaire will identify as Republicans.
Furthermore, there are no Census or official figures on party identification nationally. A number of states do not require party registration, and what a person calls himself or herself can vary significantly from week to week or month to month.
So it is incorrect to say that a poll's showing one candidate to be ahead is the result of the fact that there are too many members of his party in the sample. In fact, that there are more people identifying with a leading candidate's party is a result of the same forces that are pushing that candidate into the lead.
One final note. Gallup (and other reputable pollsters) do carefully analyze the compositions of each sample on known demographic measures for which there are solid Census figures: age, gender, region of country, ethnicity, and education. And we do weight each sample to each of these if necessary, using complex and accepted statistical procedures. So our samples are remarkably constant from poll to poll on known demographic and regional measures. But in a political year we don't expect that samples will be the same from poll to poll in terms of party identification, any more than we expect the samples to be the same from poll to poll in terms of the choice of candidate for whom the respondents are voting.
http://gallup.com/poll/content/?ci=12292
Printer-friendly format
Email this thread to a friend
Bookmark this thread
(1000+ posts)
Send PM |
Profile |
Ignore
