American Mosaic Project Survey, 2003 (ICPSR 28821)

Published: Dec 16, 2010

Principal Investigator(s):
Douglas Hartmann, University of Minnesota; Joseph Gerteis, University of Minnesota; Penny Edgell, University of Minnesota

Version V1

The survey is from the American Mosaic Project, a multiyear, multimethod study of the bases of solidarity and diversity in American life. The survey contains items measuring the place of diversity in visions of American society and in respondents' own lives; social and cultural boundaries between groups and dimensions of inclusion and exclusion; racial and religious identity, belonging and discrimination; opinions about sources of advancement for Whites and African Americans; opinions about immigration and assimilation; diversity in respondents' close-tie network; political identity and demographic information. The survey also includes oversamples of African American and Hispanic respondents, allowing for comparisons across racial/ethnic categories. Demographic variables include race, age, gender, religion, level of education, United States citizenship status, partisan affiliation, and family income. See Appendix: Project Narrative for more information.

Hartmann, Douglas, Gerteis, Joseph, and Edgell, Penny. American Mosaic Project Survey, 2003. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2010-12-16.

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote

David Edelstein Family Foundation

2003-05 -- 2003-07


The survey used a nationally representative (48 states and the District of Columbia) sample, reached by Random Digit Dialing techniques, using samples purchased from one or another of the reputable national companies (typically Survey Sampling or Genesys). It included oversamples designed to increase the number of persons of African American and/or Hispanic heritage over that which would be found in a simple national sample. The total "N" will be 2,000, targeting approximately 400 from each of the two targeted backgrounds and 1,200 persons of other racial/ethnic heritage. Oversamples were be based on the selection of areas with high incidence of African American and/or Hispanic persons, but all telephone numbers were generated at random.

The survey includes oversamples of African American and Hispanic respondents, allowing for comparisons across racial/ethnic categories. The weighted proportion of Whites, African Americans, and Hispanics is close to Census estimates, with the sample being 77 percent White, 11 percent Hispanic, and 12 percent African American.

The project consists of a random-digit dial telephone survey (N = 2,081) conducted during the summer of 2003 by the University of Wisconsin Survey Center.

survey data

Depending on the method of calculation, the response rate of the survey is between 26 percent and 39 percent, with the more conservative figure corresponding with the recommended American Association for Public Opinion Research (AAPOR) definition. See Appendix: Methodological Report for more information.



2010-12-16 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:

  • Performed consistency checks.
  • Created variable labels and/or value labels.
  • Standardized missing values.
  • Created online analysis version with question text.
  • Checked for undocumented or out-of-range codes.


Weight, as described above to equalize the different probabilities of coming into the sample based on selection of exchanges, release of replicates, response rates, respondent selection procedures, and number of households. Normed for a mean of 1.00 and a total of 2,081.0 (to match the raw "N").


Weight adjusting the age group by gender distribution from the above weighted procedure to match the corresponding distribution based on census estimates. Normed for a mean of 1.00 and a total of 2,081.0 (to match the raw "N"). DESWT was multiplied by PSWT1 to get the unnormed version of FINALWT. This weight is included for completeness. If one desires to poststratify based on a combination of variables other than age group by gender, one would create a new weight in the place of PSWT1 and use that to create the new "final" weight.


Final weight multiplicatively "correcting" for both design and sampling related components and to recover the age by gender distribution. This is the weight which is applied by default in the SPSS system file, and should normally be used. Normed for a mean of 1.00 and a total of 2,081.0 (to match the raw "N").


  • Data in this collection are available only to users at ICPSR member institutions.

ICPSR logo

This study is provided by ICPSR. ICPSR provides leadership and training in data access, curation, and methods of analysis for a diverse and expanding social science research community.