About this Poll
The UNF Florida Statewide Democratic Primary Poll was conducted and sponsored by
the Public Opinion Research Lab (PORL) at the University of North Florida Thursday, March 5
through Tuesday, March 10, 2020 by live callers via the telephone from 4 to 9 p.m. daily with a
maximum of five callbacks attempted. The sample frame was comprised of 1,502 registered
likely Democratic voters in Florida, 18 years of age or older. Likely voters were determined
through vote history (those who voted in the 2016 Democratic primary or the 2018 Democratic
primary) and a self-identified likelihood to vote. All voters who were 20 years of age and
younger were included as potentially likely since they may not have been eligible to vote
previous elections. The voters who met these requirements were then randomly contacted by
probability sampling. Respondents who answered that they would "definitely vote," "probably
vote," or “already voted” in the upcoming Florida Democratic Primary Election qualified to
participate in the survey. The phone numbers used for this survey were sourced from the
February 2020 update of the Florida voter file. UNF undergraduate students and employees
conducted interviews in Spanish and English. Data collection took place at the PORL facility
with its 27-station Computer Assisted Telephone Interviewing (CATI) system.
The margin of sampling error for the total sample is +/- 2.5 percentage points. The
breakdown of completed responses on a landline phone to a cellphone was 32% to 68%, with
less than 1% unidentified. Through hand dialing, an interviewer upon reaching the individual as
specified in the voter file asked that respondent to participate, regardless of landline telephone
or cellphone. Data were then weighted by age, race, sex, and education. Education weights
were created from the Census’ 2018 American Community Survey (ACS) estimate for the
percent of college-educated individuals in the state of Florida. Respondents ages 18 to 24 were
not weighted by education, given that they are not included in the ACS estimates for college
education. Age, sex, and race weights were created from the February update of the Florida
Voter File to match the registered Democratic likely voters in Florida. These demographic
characteristics were pulled from the voter file list. To ensure a representative sample of
registered voters, the 10 Florida designated market areas (DMAs) were stratified. In addition,
because of Miami-Dade County’s unique population, it was separately accounted for in its own
strata, creating 11 strata from the 10 DMAs. Quotas were placed on each of these stratified
areas to ensure a proportionate number of completed surveys from across the state.
All weighted demographic variables were applied using the SPSS version 26 rake
weighting function, which will not assign a weight if one of the demographics being weighted on
is missing. In this case, respondents missing a response for any of the demographic information
were given a weight of 1. There were no statistical adjustments made due to design effects.
This study had a 16% response rate. The American Association for Public Opinion Research
(AAPOR) Response Rate 3 (RR3) calculation was used which consists of an estimate of what
proportion of cases of unknown eligibility are truly eligible. This s