Final Pre-election Harris Polls: Still Too Close to Call but Kerry Makes Modest Gains

The final Harris Polls show Senator John Kerry making modest gains at the very end of the campaign in an election that is still too close to call using telephone methods of polling.. At the same time, the final Harris Internet-based poll suggests that Kerry will win the White House today in a narrow victory.

Harris Interactive’s final online survey of 5,508 likely voters shows a three-point lead for Senator Kerry. The final Harris Interactive telephone survey of 1,509 likely voters shows a one-point lead for President Bush. Both surveys are based on interviews conducted between October 29, 2004 and November 1, 2004. The telephone survey is consistent with most of the other telephone polls, which show the race virtually tied.

Both surveys suggest that Kerry has been making some gains over the course of the past few days (see Harris Polls #83 http://www.harrisinteractive.com/harris_poll/index.asp?PID=512, and #78 http://www.harrisinteractive.com/harris_poll/index.asp?PID=507). If this trend is real, then Kerry may actually do better than these numbers suggest. In the past, presidential challengers tend to do better against an incumbent President among the undecided voters during the last three days of the elections, and that appears to be the case here. The reason: undecided voters are more often voters who dislike the President but do not know the challenger well enough to make a decision. When they decide, they frequently split 2:1 to 4:1 for the challenger.

About one percentage point of the current difference probably reflects the inclusion in the online sample of people with cell phones but no landline (and therefore not included in the telephone survey) who favor Kerry by a wide margin (see The Harris Poll #86 released yesterday at www.harrisinteractive.com/harris_poll).

The surveys both suggest an increase of a few percentage points above the 51.3% turnout (of all adults) in 2000, but not as big an increase as some reports have suggested.

Another piece of evidence pointing to a likely Kerry victory is that online Harris Polls in these large, key states, which may well determine the Electoral College result, all show modest Kerry leads. However, all these leads are within the possible sampling error for these surveys. Assuming the forecast is correct, Kerry is likely to win all three large states, and almost certainly the White House along with it. The sample sizes were well over 1,000 likely voters in Florida (1,433), Pennsylvania (1,204), and Ohio (1,218).

Q: "If the presidential election were held today, for whom would you most likely vote?"

Q: "Well, if you had to say would you lean toward. . . ?"

Base: Likely Voters who express a preference (5,508)

Q: "If the presidential election were held today between George W. Bush for the Republicans, John Kerry for the Democrats and Ralph Nader as an Independent, for whom would you most likely vote?"

Q: "Well, if you had to say would you lean toward George W. Bush, John Kerry, or Ralph Nader?"

Base: Likely Voters who express a preference (1,509)

Q: "If the presidential election were held today, for whom would you most likely vote?"

Q: "Well, if you had to say would you lean toward . . . ?"

Base: Likely Voters who express a preference

* = Less than 0.5 percent.

Note: Percentages may not add up exactly to 100% due to rounding.

1. These numbers were calculated after allocating "not sure" and refusals.
2. Likely voters in the tables are defined as registered voters who:
1. Have already voted; OR
2. Were too young to vote in 2000 and are "absolutely certain" to vote; OR
3. Voted in 2000 and are "absolutely certain" to vote; OR
4. Were old enough to vote in 2000 but did not do so, but are "absolutely certain" to vote and are "extremely interested" in the election.

The Harris Poll^® was conducted by telephone within the United States between October 29 and November 1, 2004 among a nationwide cross section of 1,509 likely voters. Figures for age, sex, race, education, number of adults, number of voice/telephone lines in the household, region and size of place were weighted where necessary to align them with their actual proportions in the population.

In theory, with a probability sample of this size, one can say with 95 percent certainty that the results have a statistical precision of plus or minus 2.5 percentage points of what they would be if the entire adult population had been polled with complete accuracy. Unfortunately, there are several other possible sources of error in all polls or surveys that are probably more serious than theoretical calculations of sampling error. They include refusals to be interviewed (nonresponse), question wording and question order, interviewer bias, weighting by demographic control data and screening (e.g., for likely voters). It is impossible to quantify the errors that may result from these factors.

The Harris Poll^® was conducted online within the United States between October 29 and November 1, 2004 among a nationwide cross section of 5,508 likely voters. Figures for age, sex, race, education, region and household income were weighted where necessary to bring them into line with their actual proportions in the population. "Propensity score" weighting was also used to adjust for respondents’ propensity to be online.

The three state surveys were based on online surveys of 1,433 likely voters in Florida, 1,204 likely voters in Pennsylvania, and 1,218 likely voters in Ohio, conducted between October 29 and November 1, 2004.

In theory, with probability samples of this size, one could say with 95 percent certainty that the results with a sample size of 1200 have a sampling error of plus or minus 2.8 percentage points of what they would be if the entire adult population had been polled with complete accuracy. Unfortunately, there are several other possible sources of error in all polls or surveys that are probably more serious than theoretical calculations of sampling error. They include refusals to be interviewed (non-response), question wording and question order, and weighting. It is impossible to quantify the errors that may result from these factors. These online samples were not probability samples.

J22300B

Q439, Q440, Q442

J11351V

Q514