Frequently asked questions about AJC polling

Whom do we talk to?

Abt SRBI conducts polling telephone operations on behalf of The Atlanta Journal-Constitution. Interviews for this poll were completed with 1,157 Georgians in order to get a sample of 1003 registered voters and 839 likely voters. Of those, 65 percent were reached on cellphones. The questions were asked by live interviewers, not an automated system.

How do we get the telephone numbers?

Abt SRBI draws its sample of telephone numbers from two sources: a list of Georgia registered voters that includes cellphone or landline numbers and a list of all cellphone numbers and landline numbers with a Georgia telephone exchange.

How is it possible to get a sample that reflects all Georgians?

The pollster generates a random sample of statewide telephone numbers from the lists described above. Each number has an equal chance of being selected. The sample serves as a model of the population of the state. Interviews are conducted statewide, with geographic controls in place to ensure an equal statewide distribution of surveys is completed. Weighting ensures our final sample represents the adult population in Georgia.

So what is weighting and how do you do it?

Some adjustments are made to the total population of people surveyed in order to accurately reflect the demographics of the state. For this survey, adjustments were made for sex, age, education level, race/Hispanic ethnicity, region (North Georgia, metro Atlanta, Atlanta’s exurbs, southeast Georgia, southwest Georgia), and telephone usage (cell-only, dual-user, landline-only). Age, race and gender estimates were computed from the 2014 American Community Survey; region estimates were computed from the 2014 Census Population Estimates; and phone service use estimates were computed from the National Health Interview Survey.

What does “margin of error” mean?

No matter how carefully a poll is conducted, there will always be some measure of uncertainty when you survey a small portion of a larger population, such as the state of Georgia. The margin of error is the measure of the uncertainty in the sample. The margin of error that we report accounts for these sources of uncertainty. For example, with a margin of error of 4 percentage points, a candidate polling at 50 percent could have support of anywhere between 46 percent and 54 percent, with a 95 percent level of confidence. That means that if we drew 100 different samples using the same methodology, then no more than than 5 times out of 100 should chance variations in the sample cause the results to vary by more than 4 percentage points from the answers that would be obtained if all Georgians were polled.

Do polls predict who will win an election?

Polls provide a snapshot of where voters stand at the time they are questioned. While we are getting close to Election Day, voter sentiment could still shift.

Why do different polls get different results?

Polls can vary depending on when they were taken, how many people were interviewed and how the poll was conducted.

Who writes the questions?

Atlanta Journal-Constitution journalists work with our polling partners to create the survey. Some questions are commonly asked election questions.

Want more information about how we conducted the poll?

See myajc.com/october-2016-poll.