A poll in St Johns County sheriff race had to be re-done due to error

On Monday morning, local radio broadcast partner Kevin Geddings notified Historic City News editor Michael Gold, that his station, WSOS 103.9 Radio, had the results of polling conducted and sponsored by the Public Opinion Research Lab at the University of North Florida.

According to associate professor of political science, Dr. Michael Binder, who conducted and directed this political survey, the Public Opinion Research Lab, opened in 2001, as an independent, non-partisan center, a charter member of the American Association for the Public Opinion Research Transparency Initiative, and a member of the Association of Academic Survey Research Organizations.

“The Public Opinion Research Lab is a full-service survey research facility that provides tailored research to fulfill each client’s individual needs from political, economic, social, and cultural projects,” according to Binder.  “The University of North Florida St Johns County Poll was performed in English by live callers to Florida registered Republican voters, 18-years-old, or older.”

Aided by its 27-station Computer Assisted Telephone Interviewing system, the Public Opinion Research Lab harvested self-reported phone numbers used for this survey from publicly available records sourced from the December update of the Florida voter file.

Voter contact was reportedly made via the telephone between 4:00 p.m. and 9:00 p.m. on Monday, February 24 through Tuesday, February 25, 2020.  Undergraduate students and employees conducted the interviews from the Research Lab facility.

Although the goal is “to support sound and ethical practices in the conduct of survey and public opinion research”,  Historic City News learned that an additional 210 surveys had to be conducted – solely about the Sheriff’s race – to correct for “a typographical error in the original survey instrument”.

Several St Johns County “super voters”, who are also Historic City News subscribers, and some additional voters who were contacted by telephone from the survey team, almost immediately informed sheriff candidate Chris Strickland that the pollsters were misspelling and mispronouncing his last name.  Those voters said that they had to correct the telephone solicitor as to the names of the candidates running for office — a fatal polling flaw in a survey that is offered as a measure of the “name recognition” of a political candidate.

Yet, according to Binder, the “margin of sampling error” for the total sample is +/- 5.5 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 was weighted by age, race, sex, and education. Education weights were created from the December update of the Florida Voter File to match the active registered Republican “likely voters” in Florida for the percent of college-educated individuals in the State of Florida — estimated to be approximately 29%.

Sex, race, and age weights were also created from the December update of the Florida Voter File to match the active registered Republican likely voters in Florida. These demographic characteristics were pulled from the voter file list.

All weighted demographic variables were applied using the SPSS Version 25 rake weighting function; which Binder says will not assign a weight if one of the demographics being weighed is missing. In this case, respondents missing a response for any of the demographic information were given a weight of 1.

Reportedly there were no statistical adjustments made due to design effects. This study had a 21% 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.

Coincidentally, for an administration dogged by accusations of conflicts of interest, clandestine favoritism, missing money, and poor decisions in managing criminal investigations involving employees of the department; retiring Sheriff David Shoar, who, in this race, is financially and politically promoting Robert Hardwick as his replacement, is a graduate of the University of North Florida in Jacksonville, where the flawed survey was produced.