Democratizing access to the best data on religion since 1997
DATA ARCHIVE
DATA ARCHIVE

Archive Navigation

Summary
Codebook
Downloads
View Question Bank

Archive Categories


Sort the above Archive Category by:



Browse Alphabetically
Browse All Categories
Browse Newest Additions

File Summaries


Search Data Archive


Religion and Public Life Survey, 2008

DOI

10.17605/OSF.IO/N5RGH

Summary

This project investigated the public's attitudes on religion and public life. This survey was commissioned by the Pew Research Center for the People and the Press and produced two reports. The first report is titled "GOP Base Getting Behind McCain: The Presidential Race Draws Even," and the second report is titled "Some Social Conservative Disillusionment: More Americans Question Religion's Role in Politics." Many of the questions in this survey investigated views on the 2008 presidential election and probed the dynamics of support for John McCain and Barack Obama. In addition, this survey asked questions on a variety of topics including: public leaders and religion, political parties and religion, government funding for religious social services, universal health care, abortion, gay marriage, attitudes towards religious groups, and other topics.

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

Data File

Cases: 2905
Variables: 203
Weight Variable: WEIGHT, LLWEIGHT, COWEIGHT

The dataset contains three weight variables, which can be used to compare the combined landline and cell phone sample with the landline sample by itself and with the landline sample combined with the cell-only households. WEIGHT is used for the combined sample of all landline and cell phone interviews. LLWEIGHT is used for the landline sample only, while COWEIGHT is used for the landline sample and cell-only cases (COWEIGHT excludes those from the cell phone sample who reported having a landline telephone).

Data Collection

July 31-August 10, 2008

Funded By

The Pew Research Center for the People and the Press and the Pew Forum on Religion and Public Life

Collection Procedures

Telephone interviews conducted in English and Spanish under the direction of Abt SRBI, Inc., among a nationwide sample of 2,905 adults, 18 years of age or older, from July 31-August 10, 2008. Some 2,254 respondents were interviewed on a landline telephone, and 651 were interviewed on a cell phone, including 262 who had no landline telephone.

Sampling Procedures

"[This survey] . . . selects a random digit sample from both landline and cell phone numbers in the continental United States . . . It samples landline and cell phone numbers to yield a ratio of approximately three landline interviews to each cell phone interview.

"The design of the landline sample ensures representation of both listed and unlisted numbers (including those not yet listed) by using random digit dialing. This method uses random generation of the last two digits of telephone numbers selected on the basis of the area code, telephone exchange and bank number. A bank is defined as 100 contiguous telephone numbers; for example, 800-555-1200 to 800-555-1299. The telephone exchanges are selected to be proportionately stratified by county and by telephone exchange within the county. That is, the number of telephone numbers randomly sampled from within a given county is proportional to that county's share of telephone numbers in the U.S. Only banks of telephone numbers containing three or more listed residential numbers are selected.

"The cell phone sample is drawn through systematic sampling from dedicated wireless banks of 100 contiguous numbers and shared service banks with no directory-listed landline numbers (to ensure that the cell phone sample does not include banks that are also included in the landline sample). The sample is designed to be representative both geographically and by large and small wireless carriers.

"Both the landline and cell samples are released for interviewing in replicates, which are small random samples of the larger sample. Using replicates to control the release of telephone numbers ensures that the complete call procedures are followed for the entire sample. The use of replicates also ensures that the regional distribution of numbers called is appropriate. This also works to increase the representativeness of the sample.

"When interviewers reach someone on a landline phone, they ask to speak with 'the youngest male, 18 years of age or older, who is now at home.' If there is no eligible male at home, interviewers ask to speak with 'the youngest female, 18 years of age or older, who is now at home.' This method of selecting respondents within each household improves participation among young people who are often more difficult to interview than older people because of their lifestyles. Unlike a landline phone, a cell phone is assumed in Pew Research polls to be a personal device. This means that, for those in the cell sample, no effort is made to give other household members a chance to be interviewed. Instead, interviewers ask if the person who answers the cell phone is 18 years of age or older to determine if they are eligible to complete the survey . . . " (Pew Research Center for the People and the Press)

All of the above quotations taken from the survey methodology are available online at:
https://www.pewresearch.org/our-methods/u-s-surveys/

Principal Investigators

The Pew Research Center for the People and the Press and the Pew Forum on Religion and Public Life

Related Publications

The Pew Research Center for the People and the Press Survey Report: Presidential Race Draws Even: GOP Base Getting Behind McCain, August 13, 2008

The Pew Research Center for the People and the Press Survey Report: More Americans Question Religion's Role in Politics: Some Social Conservative Disillusionment, August 21, 2008

Comparison of landline only, cell phone only, and combined landline/cell phone samples of surveys conducted during the 2008 presidential election cycle: Cell Phones and the 2008 Vote: An Update, September 23, 2008

Related Sites:

https://www.pewresearch.org/politics/datasets/

A Note on Weighting

The combined landline and cellphone data were weighted using demographic weighting parameters derived from the March 2007 Census Bureau's Current Population Survey, along with an estimate of current patterns of telephone status in the U.S. derived from the 2007 National Health Interview Survey. An iterative technique that simultaneously balances the distributions of all weighting parameters was employed. The weighting procedure also accounted for the fact that respondents with both landline and cell phones had a greater probability of being included in the sample.

Note 1: Guide to Randomization

This survey features considerable question-order randomization as well as randomization in the order that answer choices were read to respondents. Using the randomization variables in this data set, identifiable by the prefixes RNDM and RDM, it is possible to reconstruct the order that respondents were read questions and answer choices in instances when randomization was employed. Below is a list of the variables affected by randomization and a guide to using the randomization variables to replicate the order that respondents were read questions and answer choices.

VOTE08, LEAN08: The names of the presidential candidates were rotated across the sample. Randomization variable RNDMVOTE specifies whether John McCain's or Barack Obama's name was read first in the question text.

CHNCMCCN, CHNCOBMA: These questions were read to some respondents in reverse order. Randomization variable RNDMCHNC specifies whether a respondent was asked to answer CHNCMCCN or CHNCOBMA first.

LIKEMCCN, TRBLMCCN, LIKEOBMA, TRBLOBMA: The order that these questions were read varied in the following manner: a respondent would either be read the questions LIKEMCCN, TRBLMCCN, LIKEOBMA, and TRBLOBMA (in that order) or would be read the questions LIKEOBMA, TRBLOBMA, LIKEMCCN, and TRBLMCCN (in that order). Randomization variable RNDMLITR specifies whether the questions pertaining to John McCain or the questions pertaining to Barack Obama were read first. Additionally, three of the four substantive answer choices (candidate position categories) for each of these questions were rotated across the sample. Randomization variables RDMLITR1, RDMLITR2, and RDMLITR3 specify which candidate position categories were read first, second, and third (respectively).

JGCRISIS, TYPPOL, GETDONE, SHVALUE (on Form 1); and NEWIDEA, QUALPRES, HONTRUTH, CONCTAMS, TKSTAND (on Form 2): The names of the presidential candidates were rotated across the sample. Randomization variable RNDMCHAR specifies whether John McCain's or Barack Obama's name was listed first in the text of the question. Additionally, the four above questions listed on Form 1 and the five above variables listed on Form 2 were read together as a block, and the questions within the block were read at random. Randomization variable RDMCHAR1 specifies which of these questions was read first, randomization variable RDMCHAR2 specifies the question read second, randomization variable RDMCHAR3 specifies the question read third, and randomization variable RDMCHAR4 specifies the question read fourth. Pertaining only to the questions listed on Form 2, randomization variable RDMCHAR5 specifies the question from the list above that was read fifth.

ECON, IRAQ, TERRISM, GAYMARR, MORVAL, ABRTN, ENERGY, HLTHCARE, EDUCTION, ENVIRO, IMMGTN, TRADEPOL: These questions were read together as a block but were read in a random order within the block. Randomization variables RDMISS1 through RDMISS12 specify the order in which each respondent was read these twelve questions. For example, RDMISS8 specifies which of the above twelve questions was read eighth, and RDMISS11 specifies which of the above questions was read eleventh.

HLINSALL, WORSHP: These questions were read to some respondents in reverse order. Randomization variable RDMHLWO1 specifies whether a respondent was read HLINSALL or WORSHP first, while randomization variable RDMHLWO2 specifies whether a respondent was read HLINSALL or WORSHP second.

ABORTION: The answer choices for this question were read to some respondents in reverse order. Rather than being read the answer choices as "Legal in all cases, legal in most cases, illegal in most cases, or illegal in all cases" (in that order), some respondents were read the answer choices in the following order: "Illegal in all cases, illegal in most cases, legal in most cases, or legal in all cases." Randomization variable RDMABORT indicates whether the answer choices were read in reverse order for a given respondent.

DEMFAV, REPFAV: These questions were read to some respondents in reverse order. Randomization variable RNDMFAV1 specifies whether DEMFAV or REPFAV was read first, while randomization variable RNDMFAV2 specifies whether DEMFAV or REPFAV was read second.

SRVNEED: The answer choices for this question were read in a random order. Randomization variable RNDMSRV1 specifies which of the three answer choices was read to a respondent first, randomization variable RNDMSRV2 specifies the answer choice that was read to that respondent second, and randomization variable RNDMSRV3 specifies the answer choice that was read to that respondent third.

CHRHFUND, CHARFUND: These questions were read to some respondents in reverse order. Randomization variable RDMFUND1 specifies whether CHRHFUND or CHARFUND was read first, while randomization variable RDMFUND2 specifies whether CHRHFUND or CHARFUND was read second.

BUSHVAL, CLINTVAL, OBMAVAL, MCCNVAL: These questions were read together as a block but were read in a random order within the block. Randomization variables RNDMVAL1 through RNDMVAL4 specify the order that each respondent was read these questions. For example, randomization variable RNDMVAL3 specifies which of the above questions was read third.

CRCHPOL: The two substantive answer choices to this question were rotated for some respondents. Randomization variable RNDMPOL specifies which of these two substantive answers to this question was read first.

UNCPOLIT, PRESREL: These questions were read to some respondents in reverse order. Randomization variable RNDMUNC specifies whether UNCPOLIT or PRESREL was read first.

DEMSREL, REPSREL: These questions were read to some respondents in reverse order. Randomization variable RDMPRTY1 specifies whether DEMSREL or REPSREL was read first, while randomization variable RDMPRTY2 specifies whether DEMSREL or REPSREL was read second.

CNTRLREP, CNTRLDEM: These questions were read to some respondents in reverse order. Randomization variable RDMCTRL1 specifies whether CNTRLREP or CNTRLDEM was read first, while randomization variable RDMCTRL2 specifies whether CNTRLREP or CNTRLDEM was read second.

PROTLIFE, CATHLIFE, JEWLIFE, MUSLIFE, HINDLIFE: These questions were read together as a block but were read in a random order within the block. Randomization variables RDMLIFE1 through RDMLIFE5 specify the order that each of the respondents was read these five questions. For example, RDMLIFE4 specifies which question was read to a respondent fourth.

Additionally, CATHFUND, PROTFUND, MUSLFUND, JEWFUND, MORMFUND, and EVNGFUND were read in random order, but are not associated with any randomization variables in the data set available here.

Note 2: FIPS Codes

To translate FIPS (Federal Information Professing Standards) codes, refer to the Federal Information Processing Standards Publication 6-4.

The Religion and Public Life Survey (2008) presents FIPS codes as five-digit numbers. The first two digits refer to a respondent's state and the last three digits refer to a respondent's county.

Note 3: MSA Codes

To translate MSA (Metropolitan Statistical Area) codes for 2008, refer to the Office of Management and Budget's (OMB) Bulletin No. 08-01 at the following link:
https://www.whitehouse.gov/wp-content/uploads/legacy_drupal_files/omb/bulletins/2001-2008/b08-01.pdf

A value of 0 on MSA variables represents a response of "don't know" or "refused."

Note 4: HORSE Codes

The horserace variable (HORSE) was generated using the following coding structure:

If VOTE08 = 1 or LEAN08 = 1, then HORSE = 1
If VOTE08 = 2 or LEAN08 = 2, then HORSE = 2
If LEAN08 = 3, then HORSE = 3
If LEAN08 = 9, then HORSE = 9

Note 5: SWING08 Codes

The variable SWING08 was generated using the following coding structure:

If VOTE08 = 1 and CHNCOBMA > 1, then SWING08 = 1
If VOTE08 = 2 and CHNCMCCN > 1, then SWING08 = 2
If LEAN08 = 1 or [VOTE08 = 1 and CHNCOBMA = 1], then SWING08 = 3
If LEAN08 = 2 or [VOTE08 = 2 and CHNCMCCN = 1], then SWING08 = 4
If LEAN08 > 2, then SWING08 = 5

Note 6: RELIG Protestant Description

On the variable RELIG, those who provided the following answers were coded as Protestant (RELIG = 1): Baptist, Methodist, Non-denominational [Protestant], Lutheran, Presbyterian, Pentecostal, Episcopalian, Reformed, Church of Christ, Jehovah's Witness

(This list is not exhaustive; these groups are listed as being classified as Protestant on the original questionnaire document.)

Note 7: HOLYBOOK/LITERAL Notes

When reading the questions HOLYBOOK and LITERAL, the following text is substituted for the phrase [Holy book] in the question wording and answer choices:

Insert "the Bible" if RELIG = 1-4, 9-10, or 12-13; or if CHR = 1
Insert "the Bible" if RELIG = 99 and CHR = 2 or 9
Insert "the Torah" if RELIG = 5
Insert "the Koran" if RELIG = 6
Insert "the Holy Scripture" if RELIG = 7-8 or 14, or if (RELIG = 11 and CHR = 2 or 9)

Our Sponsors

Our Affiliates

US RELIGION
WORLD RELIGION
DATA ARCHIVE
RESEARCH
TEACHING
CONGREGATIONS
ABOUT
© 2024 The Association of Religion Data Archives. All rights reserved.