A unique poll pioneered by the University of Southern California turned out to be one of the few nationally that correctly called the Presidential election.
The 2016 USC Dornsife / LA Times Presidential Election Daybreak Poll was dismissed by most in the polling profession, and by Democrats, because it almost consistently showed Republican Donald Trump in the lead.
The poll used the same panel of 3,000 randomly-selected respondents. Every day a different subset of 400 from the panel were asked questions about whether they would vote and who they would choose. This differs from traditional polling in which different respondents are called each time using random phone numbers.
“It has been an unusual election year, with unconventional candidates and campaigns — and our unusual poll,” Kapteyn and Darling said in a statement Wednesday. “For five months, we tracked a panel and were able to see the certainty of a single group of voters shift over time.”
Kapteyn, a professor of economics and public opinion expert, told the Times in an interview that even he was surprised by the success of the poll he directed.
“To be honest, I was surprised,” he admitted. “One of the ways in which other polls may have gone wrong is that they have a hard time defining who is going to vote.”
The team responsible for the Daybreak Poll four years ago developed the successful RAND Continuous Presidential Election Poll, which was based on the same methodology.
>> Subscribe to Times of San Diego’s free daily email newsletter! Click hereFollow Us: