The Lilly Survey of Attitudes and Social Network (LSASN) was designed to assess individual attitudes, social networks, and involvement in the religious life of congregations. The survey was funded by a larger grant from the Lilly Endowment, Inc. to study multiracial congregations. The survey had ambitious aims in terms of content, experimental designs, and oversampling of African Americans, Hispanic Americans, and Asian Americans. It probes respondents' racial and political attitudes and examines the racial composition of their social networks, including their religious congregations. The survey is notable for conducting the first national-level factorial telephone experiment designed to address the debate concerning neighborhood preferences by race (variable BUYHOME).
The data file available for download also contains 1990 and 2000 U.S. Census data for respondents' given zip codes. These data were merged in by the primary investigator and provide information on racial composition at the levels of tract, block, and zip code.
- Data File
- Cases: 2,561
Weight Variable: WGTEDSEX, WGTFINAL
- When wanting to do point estimates, such as frequencies, for the whole sample, use WGTFINAL. When wanting to do point estimates by racial group, use WGETEDSEX. When doing multivariate analysis, it is recommended that you not use weights, but instead include as control variables, q138a (education), race variables, male, and marital status variables.
- Data Collection
- Date Collected: October 1999 through March 2000
- Funded By
- The Lilly Endowment, Inc.
- Collection Procedures
- The telephone survey was conducted by the University of North Texas Survey Research Center. The survey was performed from October of 1999 through March of 2000, with the exception of the last three weeks in December. In the case of no answer, up to eight callbacks were performed. The instrument, which was programmed into the CATI system, was also translated into Spanish. Approximately one third (94) of the interviews completed with Hispanic respondents were conducted in Spanish. Due to the variety of Asian languages, the survey represents only English-speaking Asian Americans. In the case of refusals, two conversions were attempted. For the completed sample, slightly under 6 percent of the sample (134 respondents) were refusal conversion respondents.
When the white quota (1660) was filled, the survey introduction was changed to request to speak to non-white respondents only. The black and Hispanic quotas were filled quickly, but at the time of their completion, only 70 Asian interviews had been completed. One more week was spent attempting to identify and interview a random sample of Asian Americans. At the conclusion of the week, approximately 100 interviews had been completed. Due to money and time constraints, the remaining 110 interviews were conducted using a surname phone number list compiled by GENESYS. This method suffers from the obvious bias of missing any Asians with non-identifiable Asian surnames. It is estimated that approximately 40% of Asians are excluded by this method.
The response rate was 53 percent. Employing methods recommended by Mangione (1995) and others, the data, with proper multivariate controls, appear to be representative of the target population.
- Sampling Procedures
- Using a random list of prefixes from Survey Sampling Inc, and Random Digit Dialing for the last four digits, telephone numbers were called with the goal of speaking to the person 18 years or older who had the next birthday.
- Principal Investigators
- Michael O. Emerson
- Related Publications
- Emerson, Michael O., Karen J. Chai, and George Yancey. 2001. "Does race matter in residential segregation? Exploring the preferences of white Americans." American Sociological Review 66:922-935.
Emerson, Michael O., Rachel Tolbert Kimbro, and George Yancey. 2002. "Contact theory extended: The effects of prior racial contact on current social ties." Social Science Quarterly 83:745-761.