Pew Study Finds No Easy Fix for Bogus Respondents in Online Opt-In Polls
Pew Research Center tested three methods for removing fraudulent respondents from online opt-in polls: trap questions, CloudResearch's Sentry prescreening, and matching to a voter file. Analyzing 11,114 respondents, they found that while purging bogus cases generally reduces error, no approach is foolproof. Voter file matching actually increased error by removing valid respondents, while trap questions and prescreening performed similarly. All three methods modestly overstated Democratic support in the 2024 election, as bogus respondents tended to claim they voted for the winner, Donald Trump.
Matching an opt-in sample to voter files slightly increased error by removing mostly good respondents (e.g., those who simply declined to give their name or address).