How the GenForward poll of young Americans was conducted
The Associated Press
Sep. 05, 2016
The GenForward poll of young adults is a survey by the Black Youth Project at the University of Chicago with the Associated Press-NORC Center for Public Affairs Research. It was conducted by NORC Aug. 1-14. It is based on online and telephone interviews of 1,958 adults age 18-30 who are members of the GenForward panel, which was designed to be representative of the young adult population.
The survey includes a total of 572 interviews with African-Americans, 520 Latinos, 309 Asian-Americans and 507 non-Hispanic whites, along with 50 young people of other racial and ethnic backgrounds.
The survey was paid for by the Black Youth Project using grants from the John D. and Catherine T. MacArthur Foundation and the Ford Foundation.
The original sample was drawn from two sources. Forty-eight percent of respondents are part of NORC's AmeriSpeak panel, which was selected randomly from NORC's National Frame based on address-based sampling and recruited by mail, email, telephone and face-to-face interviews. Fifty-two percent of respondents are part of a custom panel of young adults that uses an address-based sample from a registered voter database of the entire U.S and is recruited by mail and telephone.
NORC interviews participants over the phone if they don't have internet access. With a probability basis and coverage of people who can't access the internet, GenForward surveys are nationally representative.
Interviews were conducted in English and Spanish.
As is done routinely in surveys, results were weighted, or adjusted, to ensure that responses within each group accurately reflect the group's makeup by factors such as age, sex, region and education. Results for the full sample are weighted by race so that the overall results accurately reflect the full young adult population.
No more than one time in 20 should chance variations in the sample cause the results to vary by more than plus or minus 3.9 percentage points from the answers that would be obtained if all adults age 18-30 in the U.S. were polled. The margin of sampling error is higher for subgroups.
There are other sources of potential error in polls, including the wording and order of questions.
The questions and results are available at http://www.genforwardsurvey.com/