Neighborhood Immigrant Concentration, Interview Language, and Survey Nonresponse in the National Crime Victimization Survey (NCVS)

Using restricted data from 2011 to 2014, this study examines whether neighborhood immigrant concentration and survey interview language are associated with participation in the National Crime Victimization Survey (NCVS). The findings show that survey participation in the NCVS during the study period did not differ appreciably among households and persons sampled from neighborhoods with larger shares of immigrants. This suggests that the NCVS can contribute meaningfully to knowledge about the relationship between neighborhood immigrant concentration and levels of crime, providing an important complement to studies based on crime data collected by law enforcement agencies. Interview language had a minimal impact on nonresponse among Hispanic respondents in the NCVS, but the study revealed much higher rates of nonresponse across waves among Asian household respondents who completed the NCVS in a non-English language, especially among those from neighborhoods with relatively low immigrant concentration. This suggests that greater translation support for Asian respondents could increase NCVS response rates. Replicating and extending our research with more recent NCVS data, and incorporating the new item on citizenship status, would be valuable given the continued growth in the immigrant population, increased share of immigrants who routinely speak a language other than English at home, and social and political changes that have corresponded with observed reductions in nonresponse in government-administered surveys. We encourage the Bureau of Justice Statistics (BJS) to facilitate such research by routinely making the restricted NCVS data available for researchers to use within the nation's Federal Statistical Research Data Centers and by adding interview language as a permanent fixture of the data.