Democratizing access to the best data on religion since 1997

Archive Navigation

View Question Bank

Archive Categories

Sort the above Archive Category by:

Browse Alphabetically
Browse All Categories
Browse Newest Additions

File Summaries

Search Data Archive

PRRI 2018 American Values Survey




Vandermaas-Peeler, A., Cox, D., Najle, M. B., Fisch-Friedman, M., Griffin, R., & Jones, R. P. (2020, December 26). PRRI 2018 American Values Survey.


The American Values Survey (AVS) is Public Religion Research Institute's (PRRI) annual multi-issue survey on religion, culture and public policy. The survey is conducted in the fall each year. The goal of PRRI is to help journalists, scholars, pundits, thought leaders, clergy and the public better understand debates on public policy and the religious and cultural atmosphere that is shaping American politics and society.

The 2018 American Values Survey consisted of interviews with 2,509 adults who were spread across all 50 states and Washington, D.C. A battery of questions were included to assess the results of the 2018 Midterm elections. Questions related to views on government and reasons to vote were asked on the survey. More specifically, Americans were asked to assess the presidential candidate, the FBI and special counsel. An additional section on culture -- including race, sexual harassment and immigration -- was a part of the survey.

The ARDA has added six additional variables to the original data set to enhance the users' experience on our site.

Data File

Cases: 2509
Variables: 153
Weight Variable: WEIGHT

The weighting is accomplished in two stages. Panel base weights are first calculated for each household based on the probability that the household will be selected by NORC National Frame, which is the sampling frame used in sampling households for AmeriSpeak. These household weights are then assigned to each adult in the sample. In the second stage, sample demographics are used to match the population parameters for gender, race, education, age, division, housing type and telephone usage. Telephone usage parameters was pulled from National Health Interview Survey. Other parameters are derived from an analysis of the U.S. Census Bureau's Current Population Survey.

Data Collection

September 17, 2018 - October 1, 2018

Original Survey (Instrument)

PRRI 2018 American Values Survey

Funded By

The Carnegie Corporation of New York, The Nathan Cummings Foundation, Unitarian Universalist Veatch Program at Shelter Rock, and The New World Foundation

Collection Procedures

Results from this survey were based on data collected through interviews through a mix of self-administered online tools and live telephone interviews. A random sample of 2,509 American adults (ages 18 and up) were included in this sample. All interviews were conducted among participants in AmeriSpeak, a probability-based panel run by NORC at the University of Chicago, designed to be representative of the U.S. adult population. The 109 participants who did not have Internet access were interviewed by telephone by professional interviewers. All interviews had the option of being conducted in Spanish or in English.

NORC's AmeriSpeak hosts a representative panel of civilian, non-institutional American adults. The frame was developed over a two stage probability sample design. The first stage uses National Frame Areas (NFAs), geographic areas with at least 10,000 people. The NFA has over three million households, which includes 80,000 rural households. NORC has also oversampled on adults who are hard to reach, such as Hispanics, African Americans and young adults.

Panel recruitment also happens in two stages. First, mail solicitation is sent out to randomly selected households. Telephone calls and email solicitations are used to follow up. In the second stage, any households that have not responded are provided incentives or paid a personal visit by a NORC interviewer. Members will often participate in panel surveys two to three times a month.

Sampling Procedures

The sample weighting is accomplished through iterative proportional fitting (IFP) process, which simultaneously balances the distribution of the variables. Any weight that skewed the final results were trimmed. Use of sample weights ensured that the demographic characteristics reflect the demographics of the target population.

Principal Investigators

Alex Vandermaas-Peeler; Daniel Cox; Maxine Najle, Ph.D.; Molly Fisch-Friedman; Rob Griffin, Ph.D.; Robert P. Jones, Ph.D.

Related Publications

The following link contains a summary of the Public Religion Research Institute's findings of this survey:

Our Sponsors

Our Affiliates

© 2024 The Association of Religion Data Archives. All rights reserved.