Fox News Poll Methodology Statement
Updated August 2021
Conducted under the joint direction of Beacon Research (D) and Shaw & Company Research (R), the Fox News survey includes interviews with a nationally representative sample of approximately 1,000 registered voters. About 15 percent of completed interviews are with respondents on landlines and 85 percent with respondents on cellphones.
Respondents are randomly selected from a national list of registered voters sourced from Aristotle. The survey employs a probability proportionate to size method, which means the number of respondents included in the sample in each state is proportional to the number of voters in each state.
The poll uses a dual-frame sample design encompassing landlines and cellphones. Sample for the cellphone frame is randomly selected from the full universe of voters with cellphones included in the voter file; sample for the landline frame is randomly selected from the full universe of voters with landlines numbers. The lists are "de-duped," so no voters are included twice.
In addition, all respondents are screened to ensure they are registered to vote. Before elections, interviewers sometimes screen for "likely voters" through a series of questions about past voting behavior, vote likelihood, and/or interest in the current election.
Quotas are applied to ensure the sample mirrors the proportions of voters nationally. Specifically, gender (53 percent female, 47 percent male) and regional quotas are employed.
Trained professional interviewers conduct all interviews for the Fox News Poll, and use a computer-assisted telephone interviewing (CATI) system. Both human supervisors and software monitor each step of the interviewing process.
Dialing is structured such that prospective respondents always find a live interviewer when they answer their phone. On average, six calls are placed to each unanswered number during the period when the poll is fielded -- typically three to four days.
Cellphone respondents are screened to ensure they are not driving or participating in an activity that requires their full attention.
When necessary, minor weights are used to ensure the demographics of survey respondents are representative of the national registered voter population. Generally, weights are only applied to age, race, education, and area variables. The Fox News Poll is not weighted by party identification.
For a sample of about 1,000 interviews, the error due to sampling is plus or minus 3.1 percentage points at the 95 percent confidence level. For example, when the survey says "47 percent of voters…" then the probability is very high that no less than 44 percent and no more than 50 percent of all voters would have responded the same way. Sampling error associated with subgroup results is higher.
In addition to sampling error, question wording and question order can influence results.