Poster Paper: Is Differential within Household Migration Captured Effectively with the National Change of Address (NCOA) Registry?

Thursday, November 8, 2012
Liberty A & B (Sheraton Baltimore City Center Hotel)

*Names in bold indicate Presenter

Alison K. Fields1, William K. Koerber2 and Amy O'Hara1, (1)U.S. Census Bureau, (2)US Census Bureau

This paper discusses the utility of the National Change of Address (NCOA) database in providing accurate and timely measures of the household, and individual, geographical mobility patterns in the United States, compared to the American Community Survey (ACS).  Migration flow pairs (residence origins to destinations) will be constructed for each recorded household move. We use this administrative records database matched to ACS household data for individual survey years 2006 – 2010, for which migration origin and destination pairs have also been created. We then directly examine the accuracy in reporting a move in the last year at both the household level, and the individual level, using our combined administrative and survey data. The combined data also allow us to examine individual movers within the household, to determine, how well, if at all, differential moves by household members are captured in NCOA.  We will additionally evaluate the quality of the reporting of previous address for movers in the American Community Survey, and the lag time that occurs between the two sets of data.  Household and individual characteristics as reported in the ACS data will be used to infer the likelihood of consistent match on reported move, and reported origin and destination combinations. To evaluate the use of the NCOA, we will compare migration flows both with and without imputed ACS data, to determine if the administrative records data are more accurate with the exclusion of imputed survey observations. This paper will be the first attempt at comparing migration data across these datasets.