Religion and Public Life Survey, 2009

Data Archive > U.S. Surveys > General Population > National > Pew Research Center > Summary


This project investigated the public’s attitudes on religion and public life. Interviewers asked questions on a variety of topics, including political views, attitudes towards different religions, religious discrimination and government funding of religious social service program.

The survey was commissioned by the Pew Research Center for the People and the Press and conducted in two waves (Survey A and Survey B). In Survey A, telephone interviews were conducted with a nationally representative sample of 2,010 adults living in the continental United States between August 11 and August 17, 2009. In Survey B, telephone surveys were conducted with 2,003 adults between August 20 and August 27, 2009.

The survey was conducted under the direction of Princeton Survey Research International. Interviews were conducted in English and Spanish at Princeton Data Source, LLC. Statistical results are weighted to correct known demographic discrepancies. The margin of sampling error for the complete set of weighted data is ± 2.7% and ±1.9% for Surveys A and B respectively. Details on the design, execution and analysis of the survey are discussed below.

Sources: “Methodology: 2009 Religion and Public Life Survey A" and "Methodology: 2009 Religion and Public Life Survey B," prepared by Princeton Survey Research Associates International for the Pew Research Center for the People and Press, August 2009.

Data File
Cases: 4,013
Variables: 264
Weight Variable: LLWEIGHT, COWEIGHT, WEIGHT
LLWEIGHT is applied to the landline random digit dialing (RDD) sample only. COWEIGHT is the weight for the landline RDD sample and the cell-only cases combined; cases from the cell phone RDD sample that reported having a landline phone are excluded. WEIGHT is the weight for the combined sample of all landline and cell phone interviews.
Data Collection
Date Collected: Survey A was conducted between August 11 and August 17, 2009, while Survey B was conducted between August 20 and August 27, 2009.
Funded By
The Pew Research Center for the People and the Press and the Pew Forum on Religion and Public Life
Collection Procedures
As many as seven attempts were made to contact every sampled telephone number. The sample was released for interviewing in replicates, which are representative subsamples of the larger sample. Using replicates to control the release of sample ensures that complete call procedures were followed for the entire sample. The times and days of calls were staggered to maximize the chance of making contact with potential respondents. If necessary, at least one daytime call was made to each phone number in an attempt to find someone at home. Interviewing was spread as evenly as possible across the four days in field.

For the landline sample, half of the time interviewers first asked to speak with the youngest adult male at home. If no male was at home at the time of the call, interviewers asked to speak with the youngest adult female. For the other half of the contacts interviewers first asked to speak with the youngest adult female at home. If no female was available, interviewers asked to speak with the youngest adult male at home. For the cellular sample, interviews were conducted with the person who answered the phone. Interviewers verified that the person was an adult and in a safe place before administering the survey. Cellular sample respondents were offered a post-paid cash incentive for their participation.

Sources: “Methodology: 2009 Religion and Public Life Survey A" and "Methodology: 2009 Religion and Public Life Survey B," prepared by Princeton Survey Research Associates International for the Pew Research Center for the People and Press, August 2009.
Sampling Procedures
A combination of landline and cellular random digit dial (RDD) samples was used to represent all adults in the continental United States who have access to either a landline or cellular telephone. Both samples were provided by Survey Sampling International, LLC (SSI) according to PSRAI specifications. Numbers for the landline sample were drawn with equal probabilities from active blocks (area code + exchange + two-digit block number) containing three or more residential directory listings. The cellular sample was not list-assisted, but was drawn through a systematic sampling from dedicated wireless 100-blocks and shared service 100-blocks with no directory-listed landline numbers."

Sources: “Methodology: 2009 Religion and Public Life Survey A" and "Methodology: 2009 Religion and Public Life Survey B," prepared by Princeton Survey Research Associates International for the Pew Research Center for the People and Press, August 2009.
Principal Investigators
The Pew Research Center for the People and the Press and the Pew Forum on Religion and Public Life
Related Publications
Detailed summary of Pew Forum's Methodology: http://people-press.org/methodology/about/

See the following reports from The Pew Forum on Religion & Public Life and The Pew Research Center for the People & the Press:

"Many Americans Mix Multiple Faiths: Eastern, New Age Beliefs Widespread", December 9, 2009.
"GOP Seen as Friendlier To Religion Than Democrats: Obama Seen as More Friendly Than His Party", December 1, 2009.
"Faith-Based Programs Still Popular, Less Visible: Church-State Concerns Persist", November 16, 2009.
"Majority Continues to Support Civil Unions: Most Still Oppose Same-Sex Marriage", October 9, 2009.
"Support for Abortion Slips: Issue Ranks Lower on the Agenda", October 1, 2009.
"Muslims Widely Seen as Facing Discrimination: Views of Religious Similarities and Differences", September 9, 2009.
Related Sites
The Pew Research Center for the People & the Press
The Pew Forum on Religion & Public Life
Working With Surveys A and B
The ARDA has renamed variables in the dataset to help users distinguish questions asked on Survey A from those asked on Survey B. Questions that were asked only on Survey A are identified with variable names ending in the suffix "_A" (e.g., ECON_A). Questions asked only on Survey B are identified with variable names ending in the suffix "_B" (e.g., ELECT_B). If a question was asked on both surveys, its variable name does not contain either suffix. The variables OBAMAP, COUNTRY, ABORTN, GOP, DEMS, GVFUND and PRAY were created by combining responses to questions that were asked in substantively identical ways on both Survey A and Survey B. For example, OBAMAP was created by combining responses on OBAMAP_A and OBAMAP_B. The original variable names are given in parentheses at the end of the question text.
Note on Weighting
"Weighting is generally used in survey analysis to compensate for sample designs and patterns of non-response that might bias results. A two-stage weighting procedure was used to weight this dual-frame sample. A first-stage weight of 0.5 was applied to all dual-users to account for the fact that they were included in both sample frames. Respondents who were identified as either land line only or cell phone only were assigned a first-stage weight of 1. Respondents whose phone use status could not be determined were assigned their sample’s average first-stage weight.

The first-stage of weighting also included an adjustment to landline respondents that corrected for unequal probabilities of selection based on the number of adults in the household. An adjustment factor of one was assigned to landline respondents who live with no other adults. This who live in a household with one other adult were assigned an adjustment factor of two and those living in households with more than one other adult were assigned an adjustment factor of three.

The second stage of weighting balanced sample demographics to population parameters. The sample was balanced - by form - to match national population parameters for sex, age, education, race, Hispanic origin, region (U.S. Census definitions), population density, and telephone usage. The White, non-Hispanic subgroup was also balanced on age, education and region. The basic weighting parameters came from a special analysis of the Census Bureau’s 2008 Annual Social and Economic Supplement (ASEC) that included all households in the continental United States. The population density parameter came from Census 2000 data. The cell phone usage parameter came from an analysis of the July-December 2008 National Health Interview Survey.

Weighting was accomplished using Sample Balancing, a special iterative sample weighting program that simultaneously balances the distributions of all variables using a statistical technique called the Deming Algorithm. Weights were trimmed 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 national population."

Sources: “Methodology: 2009 Religion and Public Life Survey A" and "Methodology: 2009 Religion and Public Life Survey B," prepared by Princeton Survey Research Associates International for the Pew Research Center for the People and Press, August 2009.
Note 1: MSA Codes
To translate MSA (Metropolitan Statistical Area) codes for 2009, refer to the Office of Management and Budget's (OMB) Bulletin 09-01 at the following link:
http://www.whitehouse.gov/sites/default/files/omb/assets/omb/bulletins/fy2009/09-01.pdf

A value of 0 on MSA variables represents a missing response.
Note 2: Randomization of Religious Similarity Variables
Variables SCATH_A through SHINDU_A were read together as a block, but were read in a random order within the block. Variables ACATH_A through AHINDU_A were read together as a separate block and were read in a random order within that block. In other words, all the questions in the block of variables from SCATH_A to SHINDU_A were read prior to the questions in the block of variables from ACATH_A to AHINDU_A; however, the order that the questions within each of these two blocks were read varied from respondent to respondent.

Also, the response categories for each of the two blocks of questions were read to a random half of the sample in reverse order. That is, interviewers read the response categories for questions in one of the blocks in an order beginning with "Very similar" and concluding with "Very different" for a random half of the sample, and read the response categories in an order beginning with "Very different" and concluding with "Very similar" for the other half of the sample.
Note 3: Protestant Description on RELIG and SPREL
The original questionnaire included the following list of religious groups that were to be coded on variables RELIG and SPREL as Protestant:

Baptist, Methodist, Non-denominational, Lutheran, Presbyterian, Pentecostal, Episcopalian, Reformed, Church of Christ, Jehovah's Witnesses

This list ended with "etc.," so it should not be regarded as a list of the only groups that were to be coded as Protestant.
Note 4: Definition of Household Members
For variables HH1, HH2 and ADULTS, "household members" are defined as "people who think of [the household as identified in each question] as their primary place of residence, including those who are temporarily away on busienss, vacation, in a hospital or away at school. This includes infants, children and adults."