Baylor Religion Survey, Wave II (2007)

Data Archive > U.S. Surveys > General Population > National > Baylor Religion Survey > Summary


The Baylor Institute for Studies of Religion (ISR) received a major three-year grant from the John M. Templeton Foundation, to conduct a nationally representative multi-year study of religious values, practices, and behaviors, with a specific focus on consumption of religious goods and services. Using a host of new survey items that improve upon previous work, the study will yield new data to more systematically explore and better understand what sometimes appears to be an ambiguous relationship between trust, civic engagement, and religion. In partnering with the Gallup Organization, we believe this cutting-edge study has the potential to generate data that may well cause scholars to rethink our currently used measures of religious commitment or devoutness, as well as various theories linking the influence of religion to civic engagement, spiritual capital, and many other important social and behavioral outcomes.

Data File
Cases: 1,648
Variables: 318
Weight Variable: WEIGHT
Data Collection
Date Collected: 2007
Original Survey (Instrument)
Original Baylor Survey
Funded By
The John Templeton Foundation
Collection Procedures
The self-administered survey consisted of a 16-page booklet including a cover page entitled, “The Values and Beliefs of the American Public – A National Study.” A total of 2,460 questionnaires with a cover letter explaining the study’s objectives and including a number to call if they had any questions or comments were mailed to the adults who agreed to participate in the study. Gallup then followed up with these households by sending a letter thanking them for agreeing to participate and asking for their cooperation. A follow-up reminder postcard was sent to all those who agreed to participate. A second complete mailing was also utilized for the national RDD and database sampling frame to those who did not respond to the initial mailing. Of the 624 respondents to the telephone survey, 456 completed and returned the questionnaire. Of the 1836, RDD database respondents, 1,192 respondents completed and returned the questionnaire. Gallup closed the check-in of mailed questionnaires on December 11, 2007.

For results based on the final sample of 1648, one can say with 95% confidence that the error attributable to sampling and other random effects could be plus or minus four percentage points. In addition to sampling error, question wording and practical difficulties in conducting surveys can introduce error or bias in the findings of opinion polls.
Sampling Procedures
Gallup used a mixed-mode sampling design (telephone and self-administered mailed surveys) for Wave I (2005) and Wave II (2007) of this study. First, Gallup completed 1000 telephone interviews with a national sample of the general population of adults, age 18 years of age or older. The sample used was a random digit telephone sample drawn from telephone exchanges serving the continental United States. In order to avoid various sources of bias, a random digit procedure designed to provide representation of both listed and unlisted (including not-yet-listed) numbers was used. The design of the sample ensures this representation by random generation of the last two digits of telephone numbers selected on the basis of their area code, telephone exchange and bank order. This selection procedure produces a sample that is superior to random selection from a frame of listed telephone households, and the superiority is greater to the degree that the assignment of telephone numbers to households is made independently of their publication status in the directory. Random number selection within banks ensures that all numbers within a particular bank (whether listed or unlisted) have the same likelihood of inclusion in the sample, and that the sample so generated will represent all residential (non-institutional) telephone households in the appropriate proportions.

At each household randomly selected, a Gallup interviewer attempted to conduct an interview with a selected person in the household (adult, age 18 and over who had the most recent birthday). A three-call design was used for this survey (one initial call plus two additional call-backs).

Selected questions from the self-administered survey including frequency of church attendance were included in the telephone survey. At the conclusion of the telephone survey, respondents were told that Gallup was conducting an important study on American’s values and beliefs and asked if they would be willing to participate in this study. In appreciation of their participation, potential respondents to the mail survey were offered a $5.00 incentive to complete the self-administered questionnaire and return it to Gallup. If a respondent agreed, they were asked for their mailing address. Of the 1000 respondents in the telephone survey, 662 agreed to participate, though not all agreed to give the interviewer their address. In total, 624 of the 662 who initially agreed to participate also agreed to disclosing their address for mailing purposes. Mailed surveys were sent out daily following the previous night’s recruitment interview.

In addition to the RDD phase, Gallup also mailed 1836 questionnaires to Gallup’s national RDD database (households who have been pre-selected in a random-digit dialing sample design). The recruitment phase was conducted during the period of September 4-September 29, 2007.
Principal Investigators
Christopher D. Bader
Paul Froese
Byron Johnson
F. Carson Mencken
Rodney Stark
Related Publications
Stark, Rodney. 2008. What Americans Really Believe. Waco, TX: Baylor University Press.

Froese, Paul and Christopher Bader. 2010. America's Four Gods: What We Say about God -- and What That Says about Us.. New York: Oxford University Press.
Citing the Data
When citing this study, the following information should be included:
Baylor University. 2007. The Baylor Religion Survey, Wave II. Waco, TX: Baylor Institute for Studies of Religion [producer].
Note 1
Respondent's ages were coded from their responses (in MM-DD-YYYY format) to the question "What is your date of birth?"
Note 2
For the variable JOBTITLE, respondents were instructed to enter their job title into the provided space. Investigators coded responses into the following categories: other, none, professional/managerial, secretarial/clerical, services/labor, sales/retail sales, or owner/self-employed.
Note 5
For the variable YNOTWORK, respondents were instructed to skip this question and go directly to question 76 if they had worked for pay or profit in the last week. If they had not worked for pay or profit in the last week, the were instructed to answer question 75.