Sensitive Questions, Spillover Effects, and Asking About Citizenship on the U.S. Census

Many topics social scientists study are sensitive in nature. Although we know directly asking

about these issues can lead to nonresponse, we know very little about how such questions could potentially influence responses to questions later in the survey. In this study, we use the Trump administration’s proposal to include a citizenship question on the 2020 Census to demonstrate how such spillover effects can undermine important survey-based estimates, like the number of Hispanics in the United States. Using a large survey experiment (n = 9,035 respondents), we find that asking about citizenship status significantly increases the percent of questions skipped and makes respondents less likely to report having members of their household wh  are of Hispanic ethnicity. Not only does this demonstrate how sensitive questions can have important downstream effects, but our results also speak to an important public policy debate which will likely arise again in the future.