An Examination of Imputation Patterns for Data on the Foreign-Born Population in the American Community Survey, 2006-2010

Thomas A. Gryn, U.S. Census Bureau
Edward N. Trevelyan, U.S. Census Bureau
Jeff Pongsiri, University of Maryland
Joanna Kling, University of Maryland
Megan J. Benetsky, University of Maryland
Samaneh Tabrizi, University of Maryland
Savet Hong, University of California, Berkeley

The American Community Survey (ACS) utilizes data imputation to increase data quality. Imputation involves replacing missing, incomplete, or inconsistent responses with imputed values, either through assignment or allocation. This poster analyzes the imputation patterns for data on the foreign-born population in 2006 through 2010, specifically for the variables of citizenship, year of entry, year of naturalization, and place of birth. As the poster will demonstrate, imputation differences exist between the variables when the data are analyzed across various characteristics, such as race/ethnicity and language proficiency, as well as by U.S. geographic regions.