|
Activity Number:
|
144
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 3, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
American Association of Public Opinion Research
|
| Abstract - #302883 |
|
Title:
|
Election Polling Challenges: Cell Phones, the Bradley Effect, and Voter Turnout
|
|
Author(s):
|
Scott Keeter*+
|
|
Companies:
|
Pew Research Center
|
|
Address:
|
1615 L St., NW, Washington, DC, 20036,
|
|
Keywords:
|
Election polls ; Cell phones ; Non-coverage bias ; Sensitive topics
|
|
Abstract:
|
Election polling in the 2008 presidential campaign faced many challenges, including non-coverage and non-response, the possibility that racial conservatives would be underrepresented in samples or would mislead about how they intended to vote, and greater difficulties in gauging turnout among critical groups including blacks, Hispanics and young people. Yet polls performed well nationally and statewide. Some polls had a small pro-Democratic bias in estimates for white voters, but an offsetting bias among non-whites. The potential for bias in landline pre-election surveys was confirmed by the exit poll. Among Election Day voters, 20% could have been reached by pre-election surveys only by cell phone; those with a landline phone supported Obama by only a one point margin (50%-49%), narrower than the final 6.5% margin.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
