2018 Methodology

The 2018 American Values Atlas (AVA) is a project of PRRI. Results for all demographic, religious affiliation, and political affiliation questions were based on 54,357 bilingual telephone interviews (including 32,569 cell phone interviews) conducted between January 3, 2018 and December 30, 2018 by professional interviewers under the direction of SSRS. Results for questions on specific issues (e.g., LGBTQ issues) are based on a subset of 40,292 telephone interviews (including 24,149 cell phone interviews) conducted between March 14, 2018 and December 16, 2018. Results for questions on same-sex marriage are based on a subset of 4,028 telephone interviews (including 2,413 cell phone interviews) conducted between March 14, 2018 and March 25, 2018 and between June 27, 2018 and July 8, 2018. The AVA was made possible by a generous grant from an anonymous donor with additional support from The Nathan Cummings Foundation, The Evelyn and Walter Haas, Jr. Fund, The Gill Foundation, and United Universalist Veatch Program at Shelter Rock.

Throughout 2018, at least 1,000 interviews were completed each week, with about 600 interviews conducted among respondents on their cell phones. Each week, interviewing occurred over a five- or six-day period, starting Tuesdays or Wednesdays and going through Sunday or Monday. The selection of respondents within households was accomplished by randomly requesting to speak with the youngest adult male or female currently living in the household.

Data collection was based on stratified, single-stage, random-digit-dialing (RDD) of landline telephone households and randomly generated cell phone numbers. The sample was designed to represent the total U.S. adult population from all 50 states, including Hawaii and Alaska. The landline and cell phone samples were provided by Marketing Systems Group.

The weighting was accomplished in two separate stages. The first stage of weighting corrects for different probabilities of selection associated with the number of adults in each household and each respondent's telephone usage patterns. In the second stage, sample demographics were balanced to match target population parameters for gender, age, education, race and Hispanic ethnicity, region (U.S. Census definitions), population density, and telephone usage. The population density parameter was derived from 2010 Census data. The telephone usage parameter came from an analysis of the January-June 2017 National Health Interview Survey. All other weighting parameters were derived from an analysis of the U.S. Census Bureau's March 2017 Current Population Survey.

The sample weighting was accomplished using iterative proportional fitting (IFP), a process that simultaneously balances the distributions of all variables. Weights are trimmed so that they do not exceed 4.0 or fall below 0.25 to prevent individual interviews from having too much influence on the final results. The use of these weights in statistical analysis ensures that the demographic characteristics of the sample closely approximate the demographic characteristics of the target populations.

The table below shows the sample sizes for all 50 states and 30 metro areas for both sample and issue subsample. The margin of error for the total sample is +/- 0.4 percentage points at the 95% level of confidence. The margin of error for issue subsample is +/- 0.5 percentage points at the 95% level of confidence. The margin of error for the same-sex marriage question subsample is +/-1.5 percentage points at the 95% level of confidence. The design effect for the total sample, the issue subsample, and the same-sex marriage question subsample is 1.4. In addition to sampling error, surveys may also be subject to error or bias due to question wording, context, and order effects.

Sample Sizes for States and Metro Areas