Latino National Survey (LNS), 2006 (ICPSR 20862)

Version Date: Jun 5, 2013 View help for published

Principal Investigator(s): View help for Principal Investigator(s)
Luis R. Fraga, University of Washington; John A. Garcia, University of Arizona; Rodney Hero, University of Notre Dame; Michael Jones-Correa, Cornell University; Valerie Martinez-Ebers, Texas Christian University; Gary M. Segura, University of Washington

Version V6

Slide tabs to view more

The Latino National Survey (LNS) contains 8,634 completed interviews (unweighted) of self-identified Latino/Hispanic residents of the United States. Interviewing began on November 17, 2005, and continued through August 4, 2006. The survey instrument contained approximately 165 distinct items ranging from demographic descriptions to political attitudes and policy preferences, as well as a variety of social indicators and experiences. All interviewers were bilingual, English and Spanish. Respondents were greeted in both languages and were immediately offered the opportunity to interview in either language. Interviewers also provided a consent script that allowed respondents to opt out of the survey. Demographic variables include age, ancestry, birthplace, education level, ethnicity, marital status, military service, number of people in the household, number of children under the age of 18 living in the household, political party affiliation, political ideology, religiosity, religious preference, race, and sex.

Fraga, Luis R., Garcia, John A., Hero, Rodney, Jones-Correa, Michael, Martinez-Ebers, Valerie, and Segura, Gary M. Latino National Survey (LNS), 2006. Inter-university Consortium for Political and Social Research [distributor], 2013-06-05.

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote
Ford Foundation, Russell Sage Foundation, National Science Foundation, Irvine Foundation, Hewlett Foundation, Carnegie Corporation, Joyce Foundation, W. K. Kellogg Foundation, Texas A&M University, Annie E. Casey Foundation, University of Notre Dame. Inter-University Program for Latino Research

Public and restricted versions of the data are included in this collection. Due to the sensitive nature of the restricted data, users must complete an agreement for the use of confidential data, specify the reasons for the request, and obtain IRB approval or notice of exemption for their research.

Inter-university Consortium for Political and Social Research

2005-11-17 -- 2006-08-04
  1. This study is related to ICPSR study 24502: Latino National Survey (LNS)--New England, 2006 and ICPSR study 6841: Latino National Political Survey, 1989-1990. While these studies do not constitute a formal series, these studies are related by topic and principal investigator.

  2. This study has both public use and restricted use versions. The restricted use version contains the FIPS codes which were recoded to a 9-series in the public use file.

  3. For more information on FIPS code please go to the United States Census Bureau American National Standards Institute (ANSI) Codes site.


The sample was stratified by geographic designation, meaning that each state sample was a valid, stand-alone representation of that state's Latino population. State sample sizes varied based in part on funders' recommendations, but all national figures reported were appropriately weighted such that the numbers were accurately representative of the universe covered by the study. The national margin of error was approximately plus or minus 1.05 percent. The smallest sample size for any unit was 400, yielding a margin of error of less than plus or minus 5 percent for each state. A number of states were stratified internally. In each case but California, internal strata were represented proportionately in the final sample, and imposed solely to ensure that lower density regions were in the final sample. In California, additional strata were imposed in a nonproportional fashion, owing in part to the larger sample size, to allow greater between-region comparisons. All state-level results were computed using state-level weights such that they remained representative of the state population.

The universe of analysis contains approximately 87.5 percent of the United States Hispanic population. States were first selected based on the overall size of the Latino/Hispanic population. In addition, four states, Arkansas, Georgia, Iowa, and North Carolina, were added in an attempt to capture the evolving nature of emerging populations in states without lengthy histories of large Latino populations. Georgia and North Carolina, however, rank 12th and 14th, respectively, in terms of Latino population size and would have been included on that basis alone.



2018-02-15 The citation of this study may have changed due to the new version control system that has been implemented. The previous citation was:
  • Fraga, Luis R., John A. Garcia, Rodney Hero, Michael Jones-Correa, Valerie Martinez-Ebers, and Gary M. Segura. Latino National Survey (LNS), 2006. ICPSR20862-v6. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2013-06-05.

2013-06-05 Contextual variables were added to both the public- and restricted-use versions. The original and contextual variables make public-use files found in part 3 and restricted-use files found in part 4.

2012-06-06 Updated restricted use dataset containing actual FIPS codes. This will replace the previous restricted use dataset. The FIPS codes are more extensive as they now contain information down to the tract level.

2010-05-26 Corrected variable labels on new weight variables.

2010-03-26 The PI supplied revised weight variables to be used with the study. Variables WT_METRO, WT_STATE, and WT_NATION were replaced with WT_METRO_REV, WT_STATE_REV, and WT_NATION_REV.

2010-01-05 Added restricted use dataset containing actual FIPS codes.

2008-05-27 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:

  • Created online analysis version with question text.

The principal investigators conducting the Latino National Survey contracted Latin Force Group LLC (formerly Geoscape(R) International) in October 2006 to enhance the survey respondent file with respondent weights for use in statistical analysis. The original weights for 8,634 records were based on a comparative analysis of the respondents' demographics versus each geographical stratum's overall Hispanic demographics. Subsequently in October 2007, the researchers requested that respondent weights reflect not only the overall demographic composition of respondents (versus state and national Hispanic demographics from Geoscape American Marketscape DataStream 2006), but also reflect the location where the respondents reside so regional differences in opinions and attitudes may be analyzed during state and national summary analytics. Please refer to the Appendix II: Weight Documentation section of the codebook for further information.

WT_METRO_REV: Revised study area ("Metro") respondent weight for summarizing within the Metro Area sampling geographies. This includes rural and "other" sampling areas. These weights are calibrated so the unweighted sample N (8,634) = weighted sample N within each of the 35 geographical strata. The Metro weight is equal to the state weight when the state contains only one sampling area (i.e., Arizona, Arkansas, Iowa, New Jersey, New Mexico, New York, and North Carolina).

WT_STATE_REV: Revised respondent weight for summarizing within the state. These weights are calibrated so the unweighted sample N (8.634) = weighted sample N within each state. This weight is not applicable for the multi-state DC Metro area.

WT_NATION_REV: Revised respondent weight for summarizing within the United States. The 15 states and DC Metro area included in the sample are home to 87.5 percent of Hispanic adults in the United States. This weight allows statistical comparisons to the total United States Hispanic adult population. These weights are calibrated so the unweighted sample N (8,634) = weighted sample N for the multiple states survey area.



RCMD logo

This study is provided by Resource Center for Minority Data (RCMD).