Leading research organization explains difference in New Hampshire primary projections vs. results

GLASTONBURY, Conn., Jan. 10, 2008 -- With the exception of Senator Clinton's results, New Hampshire's pre-primary polls were surprisingly accurate --- with estimates of around 36% for Senator Obama, 19% for Senator Edwards, and 6% for Governor Richardson (compared to final estimates of 36%, 17% and 5%, respectively). There is now a focus on the "inaccuracy" of pre-election polls, especially those of the Democratic presidential primary. While the research profession will review the results to better understand why Senator Clinton's poll numbers were wrong, the Marketing Research Association ( wants to emphasize that these results should not question the validity nor the value of research.

MRA issues this release to help explain the forces shaping the discrepancies between the pre-election polls and the actual outcomes in New Hampshire --- and to apply that understanding to upcoming state primaries. MRA agrees with many points made by AAPOR.

-- Polling is a scientific process that attempts to capture information about individual attitudes and behaviors, both of which can vary over time. Events that occur after a survey or poll is taken can cause changes in opinion and behavior.

-- Polls and surveys are subject to multiple sources of error --- including social desirability bias --- that some have suggested may lead to inflated estimates for some candidates.

-- The role of undecideds in a close election is difficult to predict. As late as Monday, January 7, polls indicated that up to 10% of Democratic voters were still undecided and the CBS News Polls cited that "28% of Democratic voters say their minds could still change."

-- "Margins of error" must be considered when evaluating surveys. "Margins of error" are attributable to polling questions, methodologies, and sample.

While political surveys take a snapshot of the electorate at a specific point in time, they are not an election. Campaigns are fluid entities; activities/occurrences can change the way people view candidates after surveys are conducted.

Note: American Association of Public Opinion Research (AAPOR) shared some of these points with MRA. For more information, visit

Marketing Research Association is the leading and largest association of the opinion and marketing research profession, a multi-billion dollar a year industry dedicated to providing valuable information to guide the decisions of companies that provide products and services to consumers and businesses. For more information, visit

DSS Home |  About Us |  Contact Us |  Site Index |  Subscribe | What's New
Please Tell 
Your Friends about DSSResources.COM Copyright © 1995-2021 by D. J. Power (see his home page). DSSResources.COMsm was maintained by Daniel J. Power. See disclaimer and privacy statement.