Election Results Further Validate Efficacy of Harris Interactive’s Online Methodology

Probability samples no longer required for accuracy

ROCHESTER, NY – November 6, 2008 – (NASDAQ:HPOL) - The Harris Poll® issued its final presidential popular vote predictions late on election eve: Senator Obama 52% - Senator McCain 44%. Although the final voting results are not in, the most current data available indicate that Obama won by 53% to McCain’s 46%, showing our predictions to be fairly close.

"The 2008 presidential election provided us with a unique opportunity to further prove the effectiveness of our online survey methods," said Kimberly Till, CEO of Harris Interactive. "Election predictions are highly public tests of the efficacy of any methodology, and Harris Interactive proved once again that our online research methods are fast, are very accurate, and are equal to, if not better than the best in the industry."

Although the results aren’t final, we believe that our other predictions also were accurate, including:

  • "It will be the first time that the winning candidate has won more than half the votes since … 1988." (53%)
  • "Obama’s margin of victory is likely to result in Obama winning between 350 and 380 Electoral College votes". (current estimate is 364 electoral votes)

Also, the many demographic vote predictions in The Harris Poll, were almost all very close to the exit poll numbers published by CNN:

Demographic

Obama

McCain

 

Harris Poll

CNN Exit Polls

Harris Poll

CNN Exit Polls

Male

50%

49%

45%

48%

Female

53%

56%

43%

43%

2004 Bush voter

15%

18%

82%

81%

2004 Kerry Voter

87%

89%

10%

9%

Republicans

11%

9%

88%

89%

Democrats

87%

89%

11%

10%

Independents

51%

52%

42%

44%

East

59%

59%

39%

40%

Midwest

50%

54%

45%

44%

South

47%

46%

49%

53%

West

53%

55%

40%

42%

These results provide further evidence of the accuracy and reliability of the methods used by Harris Interactive to conduct marketing and opinion research online, consistent with our good track record in predicting more than 70 elections over the last eight years.

"There is much uncertainty about the future of telephone polls because of their very low, and still declining, response rates, the large and increasing number of people with no landlines and the difficulties and costs involved with adding samples of the "cell-phone only" population," said Humphrey Taylor, Chairman of The Harris Poll. "This election further confirms that well managed, panel-based online polls are a reliable and accurate way of measuring public opinion and predicting elections. They will be more widely used in the future."

Table taken from Real Clear Politics, November 5, 2008

General Election McCain vs. Obama

Poll

Field Date(s)

Sample Size/ Mode

Margin
of Error

Obama

McCain

Difference

Actual Voting Results
(as of 11/5/08)

11/4

119.8 million

-

53%

46%

Obama +7

The Harris Poll

10/29 – 11/03

5,210/ online**

*

52%

44%

Obama +8

RCP Average

10/29 - 11/03

--

 

52.1

44.5

Obama +7.6

Marist

11/03 - 11/03

804/Tel

4.0

52

43

Obama +9

Battleground (Lake)*

11/02 - 11/03

800/Tel

3.5

52

47

Obama +5

Battleground (Tarrance)*

11/02 - 11/03

800/Tel

3.5

50

48

Obama +2

Rasmussen Reports

11/01 - 11/03

3000/Tel

2.0

52

46

Obama +6

Reuters/C-SPAN/Zogby

11/01 - 11/03

1,201/Tel

2.9

54

43

Obama +11

IBD/TIPP

11/01 - 11/03

981/Tel

3.2

52

44

Obama +8

FOX News

11/01 - 11/02

971/Tel

3.0

50

43

Obama +7

NBC News/Wall St. Jrnl

11/01 - 11/02

1011/Tel

3.1

51

43

Obama +8

Gallup

10/31 - 11/02

2,472/Tel

2.0

55

44

Obama +11

Diageo/Hotline

10/31 - 11/02

887/Tel

3.3

50

45

Obama +5

CBS News

10/31 - 11/02

714/Tel

--

51

42

Obama +9

ABC News/Wash Post

10/30 - 11/02

2,470/Tel

2.5

53

44

Obama +9

Ipsos/McClatchy

10/30 - 11/02

760/Tel

3.6

53

46

Obama +7

CNN/Opinion Research

10/30 - 11/01

714/Tel

3.5

53

46

Obama +7

Pew Research

10/29 - 11/01

2,587/Tel

2.0

52

46

Obama +6

** 3,946 likely voters

* All sample surveys and polls, whether or not they use probability sampling, are subject to multiple sources of error which are most often not possible to quantify or estimate, including sampling error, coverage error, error associated with nonresponse, error associated with question wording and response options, and post-survey weighting and adjustments. Therefore, Harris Interactive avoids the words "margin of error" as they are misleading. All that can be calculated are different possible sampling errors with different probabilities for pure, unweighted, random samples with 100% response rates. These are only theoretical because no published polls come close to this ideal.

Methodology

This Harris Poll® was conducted online within the United States between October 30 and November 3, 2008 among 5,210 adults (aged 18 and over), of whom 3,946 were likely voters. Figures for age, sex, race/ethnicity, 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.

About Harris Interactive

Harris Interactive is a global leader in custom market research. With a long and rich history in multimodal research, powered by our science and technology, we assist clients in achieving business results. Harris Interactive serves clients globally through our North American, European and Asian offices and a network of independent market research firms. For more information, please visit https://harrisinteractives.com/.

Media contact:

Carol Fricke
Corporate Communications
Harris Interactive Inc.
585.214.7479
800.866.7655 x7479
press@harrisinteractive.net

News by Date
2009
2008
2007
2006
The Harris Poll
Financial Times / Harris Poll
Events
Newsletters
Media Coverage
Client News
Media Resources
Search News Room



Print
PRIVACYSURVEY DEMOESOMAR 26 QUESTIONSJOIN OUR PANELSITE MAPSEARCH

©2009 Harris Interactive Inc. All rights reserved.