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


Portraits of American Life Study, Merged Dataset, 2006-2012

DOI

10.17605/OSF.IO/6CEDV

Citation

Emerson, M. O., & Sikkink, D. H. (2020, May 12). Portraits of American Life Study, Merged Dataset, 2006-2012.

Summary

The Portraits of American Life Study (PALS) is an extensive, national-level panel study focused on religion in the U.S., with a particular focus on capturing ethnic and racial diversity. PALS seeks to understand the impact of religion in everyday life, and ultimately the connections between religious change and other forms of change in individuals and families over the course of their lives and across generations. It includes substantive modules on family relationships, deviance, health, civic participation and volunteering, moral and social attitudes, and race and ethnic issues. It currently includes two waves, collected in 2006 and 2012. This file contains only the respondents who were in both waves (N=1,314).

ARDA Note: The ARDA coded the variable names in a way that is easy to identify across waves. The variable names have stems (e.g., CA23), and the suffix (e.g., W1) will tell you the wave of the corresponding variable. "W1" refers to Wave 1, "06" refers to Wave 1 variables that may not have been in the original Wave 1 dataset, and no suffix means that the variable is a Wave 2 variable. For example, CA23W1 belongs to Wave 1 and CA23 belongs to Wave 2. In all instances, examine the variable description, which contains the wave information (e.g., [Wave 2]) and the full question wording.

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

Data File

Cases: 1314
Variables: 1789
Weight Variable: LOWEIGHT, PLOWEIGH

In order to compensate for known biases, such as non-response, which can vary for different subgroups of the population, the sample data are weighted. The demographic weighting parameters are derived from a special analysis of the Census Bureau's American Community Survey, 2005 and 2011. These analyses produced population parameters for the demographic characteristics of adults 18 or older, which were then compared with the sample characteristics to construct sample weights. The longitudinal weights are adjusted to account for non-response in Wave 2. The "raking" technique was used, meaning it adjusts the weights to match the population proportions through an iterative process (i.e., it performs the same set of steps multiple times). The variable LOWEIGHT is sample scaled and the variable PLOWEIGH is population-scaled. Use PSWEIGHT for population estimates.

Data Collection

Wave 1: April to October, 2006. Wave 2: April to October, 2012.

Funded By

Lilly Endowment Inc.
Kinder Institute, Rice University
University of Notre Dame

Collection Procedures

Approximately 75 percent via web, 17 percent via phone, and eight percent via face-to-face interviews.

Sampling Procedures

The target population for this study is defined as the civilian, non-institutionalized population of the US who are 18 years of age or older at the time of the survey.

Wave II (2012) was conducted by Abt SRBI. The goal was to survey as many of the original sample as possible. Advance letters were mailed to all households informing respondents of the upcoming survey. Most respondents were given a choice of whether they would like to conduct the interview via the web or telephone. The interview averaged 75 minutes in length. Respondents received a gift for their time--$30 for a telephone interview, and $50 otherwise.

To test for mode effects, however, some respondents were randomly assigned the web or telephone mode of interview. Subsequent analysis of mode effect found very small bias and only for a few select variables (see mode effect document for detailed analysis).

To increase the response rate to more than 50 percent, interviewers were sent across the country to find 2006 respondents who had not completed the 2012 interview. Approximately 100 interviews were completed in this manner.

In addition to the original PALS respondents, 103 now-adult-children of 2006 respondents were interviewed. These were children of 2006 PALS respondents who were in 2012 age 20 or more. These 103 are not part of the 1,314 total of 2006 PALS respondents re-interviewed in 2012. They are new additions.

The 2012 response rate of 50.3 percent is calculated based on all respondents in the 2006 Wave. However, slightly over four perecnt of the 2006 respondents had either died by 2012 or were so severely mentally incapacitated that they were incapable of responding to the survey. The adjusted response rate, removing these cases, is 53 percent.

Principal Investigators

Michael O. Emerson, Rice University
David H. Sikkink, University of Notre Dame

Notes

When citing this study, the following information should be included:
Emerson, Michael O., and David Sikkink. Portraits of American Life Study, 2nd Wave, 2012.

OR for the longitudinal data:
Emerson, Michael O., and David Sikkink. Portraits of American Life Study, 2006-2012.

Our Sponsors

Our Affiliates

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