Winthrop University: Winthrop Poll - Current Poll Methodology
Contact Information
Winthrop Poll
10 Dinkins Hall
Rock Hill, SC 29733, USA

Methodology Statement


Survey Methodology

February 21, 2020 Winthrop Poll

These results represent the responses of 443 Likely Voters for the Feb. 29 SC Democratic Presidential Primary. Results that use all respondents have a margin of error of +/- 4.7% at the 95% confidence level. Results that use only African American respondents have a margin of error of +/- 5.9% at the 95% confidence level.

Calls were made between 2/9 - 2/19, 2020 Margins of error are based on weighted sample size and account for design effects.
Phone calls were made primarily during weekday evenings, all day Saturday, and Sunday afternoon and evening. Conducting weekend calls is important to avoid systematically excluding certain populations (such as those who may work 2nd or 3rd shift during the week). The prolonged dates are due to two other large survey projects going on at the same time.

The survey used sample of Registered Voters in South Carolina supplemented by a sample of voters who had voted in a previous primary.  All samples were purchased from Dynata (formerly Survey Sampling International). 

Data are weighted based on age, sex, race, and education.

Phone numbers selected for the survey were re-dialed up to 4 times in an attempt to reach a respondent. Surveys were conducted in English.  

Computerized autodialers were not used in order to ensure the survey of wireless phones complied with the Telephone Consumers Protection Act and all FCC rules regarding contacting wireless telephones.  73% of the completions came from the wireless sample.

View full survey instrument HERE (PDF - 55.1 KB)

The Winthrop Poll is paid for by Winthrop University.


Winthrop Poll Logo

Last Updated: 2/28/20