Barack Obama wins Iowa and is predicted to win New Hampshire according to Gallup polls. Then Hillary Clinton wins New Hampshire. Why were Gallup poll predictions wrong?
The Statistical Modeling blog tries to make sense of this in their post “What was going on with the New Hampshire polls?” The post gives three reasons why the Gallup polls could have been wrong:
- The likely voter screen and its potential deficiencies. The Gallup polls only count the opinions of people they deem to be “likely voters” and thus the polls may have incorrectly included or excluded people.
- Problems in survey weighting, especially when Iowa turnout was so strange. Surveys weight their responses in order that the poll results are more representative of the voting public. The survey designers may have incorrectly weighted the observations.
- Obama being black. “Some people have a theory that people will lie in a poll and say they support the black candidate because they don’t want to seem racist, but then they actually vote for the white person.”