The L.A. Times looks at 14 polls released in the final 10 days of the campaigns for governor and U.S. Senate and says the one that came closest to the final numbers was — ta-dahhh — its own LAT-USC poll. The Field Poll came next closest. The least accurate were the Rasmussen polls done for Fox News and Rasmussen’s own website — they agreed that Brown and Boxer were winning, but by the smallest margin of any polls.
Several differences could account for the gap among the polls. The polls that did best are ones that used the traditional method of live interviewers calling people and interviewing them on the telephone. The Field Poll and the Times/USC poll called both landlines and cellphones.
Some of the polls that were in the less-successful group are so-called robo-polls that use automated interviews. Those polls have been reasonably successful in the past, but some polling analysts this year said they thought the robo-polls were producing results that were too weighted toward Republican candidates.
Another point of difference involves the models that pollsters use to determine which voters are likely to actually cast ballots. The Times/USC survey based its likely voter model on questions about a person’s enthusiasm about voting this year, the respondent’s expressed certainty about voting and his or her voting history. Some Republican analysts said that the emphasis on past voter history was screening out Republicans who had not voted in 2006 and 2008 but who would show up this year. In the end, those hypothetical voters turned out to be something of a mirage. Exit polls this year showed an electorate that was quite similar to the group that voted in the 2006 midterm elections.
The LAT-USC polls, remember, are done jointly by Democratic and Republican polling firms.