Question

About this Poll
These findings are based on the latest WMUR Granite State Poll, conducted by the University of New Hampshire Survey Center and funded by WMUR‐TV, Manchester, NH. Nine hundred and seven (907) randomly selected New Hampshire adults were interviewed in English by landline and cellular telephone between October 11 and October 17, 2016. If a household included more than one adult, the adult who had the most recent birthday was selected to be interviewed.

The margin of sampling error is +/‐ 3.3 percent for the entire sample. Included were seven hundred seventy (770) likely 2016 general election voters (MSE +/‐ 3.5%). These MSE’s have not been adjusted for design effect. The design effect for the survey is 1.1%.

The random sample used in the WMUR Granite State Poll was purchased from Marketing Systems Group (MSG), Horsham, PA. MSG screens each selected telephone number to eliminate non‐working numbers, disconnected numbers, and business numbers to improve the efficiency of the sample, reducing the amount of time interviewers spend calling non‐usable numbers.

The data have been weighted to adjust for numbers of adults and telephone lines within households. Additionally, data were weighted by respondent sex, age, and region of the state to targets from the most recent American Community Survey (ACS) conducted by the U.S. Census Bureau. In addition to potential sampling error, all surveys have other potential sources of non‐ sampling error including question order effects, question wording effects, and non‐response. Due to rounding, percentages may not sum to 100%. The number of respondents in each demographic below may not equal the number reported in cross‐ tabulation tables as some respondents choose not to answer some questions.