The self-response rate is a key driver of the cost and quality of a census. The addition of a citizenship question to the 2020 Census could affect the self-response rate. We predict the effect of the addition of a citizenship question on self-response by comparing mail response rates in the 2010 Census, which did not have a citizenship question, and the 2010 American Community Survey (ACS), which included a citizenship question for the same housing units. To distinguish a citizenship question effect from other factors, we compare the actual ACS-Census difference in response rates for households that may contain noncitizens to the ACS-Census difference for all-U.S. citizen households. We estimate the addition of a citizenship question will have a 5.8 percentage point (ppt) larger effect on self-response rates in households that may have noncitizens relative to all-U.S. citizen households. Noncitizens are also 36.2 ppts less likely to report citizenship status that is consistent with administrative records compared to citizens. Only 6.2 ppts of this difference is explained by observed characteristics.