Working Paper: NBER ID: w16536
Authors: Greg Kaplan; Sam Schulhofer-Wohl
Abstract: We show that much of the recent reported decrease in interstate migration is a statistical artifact. Before 2006, the Census Bureau's imputation procedure for dealing with missing data inflated the estimated interstate migration rate. An undocumented change in the procedure corrected the problem starting in 2006, thus reducing the estimated migration rate. The change in imputation procedures explains 90 percent of the reported decrease in interstate migration between 2005 and 2006, and 42 percent of the decrease between 2000 (the recent high-water mark) and 2010. After we remove the effect of the change in procedures, we find that the annual interstate migration rate follows a smooth downward trend from 1996 to 2010. Contrary to popular belief, the 2007{ 2009 recession is not associated with any additional decrease in interstate migration relative to trend.
Keywords: interstate migration; imputation; current population survey
JEL Codes: C81; C83; J11; R23
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Census Bureau's change in imputation methodology in 2006 (C80) | significant reduction in the estimated interstate migration rate (R23) |
| Census Bureau's change in imputation methodology in 2006 (C80) | accounts for 42% of the decrease in interstate migration from 2000 to 2010 (R23) |
| prior to 2006, imputation procedures inflated migration rates (J11) | imputed data showed rates three to five times higher than nonimputed data (C80) |
| 2007-2009 recession (F44) | no correlation with additional decrease in interstate migration (R23) |
| change in imputation methods (C36) | nonimputed data provide a more accurate representation of migration trends (J60) |
| imputation procedures (C26) | distorted perceived trends in migration (F22) |