November 2015 Winthrop Poll of SC Residents
The November 2015 Winthrop Poll interviewed 832 Likely
Voters in the 2016 SC Democratic Presidential Primary (aged 18 and older,
registered to vote, screened for likelihood of voting in SC Democratic Presidential
Primary). Results which use all respondents have a margin of error of
approximately +/- 3.4% at the 95% confidence level. Results that use less
than the full sample will naturally have a higher margin of error.
Results for women only have a margin of error of approximately +/-4.4%. Results
for men only have a margin of error of approximately +/-5.4%. Results for African
Americans only have a margin of error of approximately +/-4.7%. Results for
whites only have a margin of error of approximately +/-5.4%. Results for Clinton
supporters only have a margin of error of approximately +/-4.1%. Results for Sanders
supporters only have a margin of error of approximately +/-8.8%. Margins of
error are based on weighted sample size.
The survey was in the field from 10/24-11/1, 2015. Phone calls were made during
weekday evenings, all day Saturday, and Sunday afternoon and evening. Weekday
daytime calls are not made to avoid oversampling those who are more likely to
be at home during the day (e.g. retirees, stay-at-home-parents, etc.).
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 survey used (1) Registration Based
Sample (RBS) of previous Democratic Primary voters,(2) Random Digit
Dialing (RDD), and (3) Wireless phone number
sampling. Both RDD and wireless samples are crucial to ensure no adult in
the geographical area of interest is systematically excluded from the
sample simply because their number is not listed in the previous voter
sample. MOST IMPORTANTLY, RDD and Wireless are necessary to capture
any voters who are likely to vote in this contest, but did not vote in previous
primaries (e.g. new to SC, newly registered voters, more interest in this
contest, etc.) Both the RDD sample and the wireless sample were purchased
from Survey Sampling International (SSI). RBS sample was purchased from
Aristotle/Voter Lists Online.
Phone numbers selected for the survey were re-dialed five or more times in an
attempt to reach a respondent. Once a household was reached, we also
employed procedures to randomize within households for RDD
sample. Numbers reached via RBS asked for specific randomly selected
voters. Surveys were conducted in English.
we screen for voter registration status, screen for
certainty of up-to-date registration status, screen OUT Republicans
and Republican-Leaning Independents, screen for
likelihood of voting, and weight by sex, age, and race.
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.
The Winthrop Poll is paid for by Winthrop University with
additional support from The West Forum on Politics and Policy at Winthrop
Additional Explanation of RDD Methodology : (with
descriptions taken from SSI website)
Samples are generated using a database of "working
blocks." A block (also known as a 100-bank or a bank) is a set of 100
contiguous numbers identified by the first two digits of the last four digits
of a telephone number. For example, in the telephone number 203-567-7200,
"72" is the block. A block is termed to be working if some specified
number of listed telephone numbers are found in that block.
of random numbers distributed across all eligible blocks in proportion to their
density of listed telephone households are selected. All blocks within a county
are organized in ascending order by area code, exchange, and block number. Once
the quota has been allocated to all counties in the frame, a sampling interval
is calculated by summing the number of listed residential numbers in eligible
blocks within the county and dividing that sum by the number of sampling points
assigned to the county. From a random start between zero and the sampling
interval, blocks are systematically selected in proportion to their density of
listed households. Once a block has been selected, a two-digit number is
systematically selected in the range 00-99 and is appended to the exchange and
block to form a 10-digit telephone number.