The American Spectator

Print Email

Text Size

The Spectacle Blog

One of the most suprising events in all of last year's election season was Hillary Clinton's upset win in the the New Hampshire primary. I remember running into Andrew Smith, director of the University of New Hampshire poll, in a sandwich shop on Elm Street in Manchester on the day of the primary. He confidently anticipated an Obama win of at least 8 points, and perhaps one in the double digits. Like many reporters, I went to the Clinton rally that night expecting to be writing her political obituary, and instead stared at the television screens in disbelief as her lead held with more and more precinct data flowing in. Today, the American Association for Public Opinion Research has released a detailed 123-page report attemting to determine what happened.

Among the highlights:

• Given the compressed caucus and primary calendar, polls conducted before the New Hampshire primary may have ended too early to capture late shifts in the electorate's preferences there.

• Most commercial polling firms conducted interviews on the first or second call, but respondents who required more effort to contact were more likely to support Senator Clinton. Instead of continuing to call their initial samples to reach these hard‐to‐contact people, pollsters typically added new households to the sample, skewing the results toward the opinions of those who were easy to reach on the phone, and who more typically supported Senator Obama.

• Non‐response patterns, identified by comparing characteristics of the pre‐election samples with the exit poll samples, suggest that some groups who supported Senator Clinton--such as union members and those with less education--were under‐ represented in pre‐election polls, possibly because they were more difficult to reach.

• Variations in likely voter models could explain some of the estimation problems in individual polls. Application of the Gallup likely larger error than was present in the unadjusted data. The influx of first-time voters may have had adverse effects on likely voter models.

Mark Blumenthal has more.