This article examines the properties and prevalence of measurement
error in longitudinal earnings data. The analysis compares matched
Current Population Survey data to administrative Social Security
payroll tax records. In contrast to typically assumed properties
of measurement error, the results indicate that errors are serially
correlated over 2 years and negatively correlated with true earnings
(i.e., mean reverting). In a cross section, the ratio of the variance
of the signal to the total variance is .82 for men and .92 for women.
These ratios fall to .65 and .81 when the data are specified in first
differences. Longitudinal earnings data may be more reliable than
previously believed.
%0 Journal Article
%1 bound1991extent
%A Bound, John
%A Krueger, Alan B.
%D 1991
%J Journal of Labor Economics
%K socdes
%N 1
%P 1-24
%T The Extent of Measurement Error in Longitudinal Earnings Data: Do
Two Wrongs Make a Right?
%U http://www.jstor.org/stable/2535111
%V 9
%X This article examines the properties and prevalence of measurement
error in longitudinal earnings data. The analysis compares matched
Current Population Survey data to administrative Social Security
payroll tax records. In contrast to typically assumed properties
of measurement error, the results indicate that errors are serially
correlated over 2 years and negatively correlated with true earnings
(i.e., mean reverting). In a cross section, the ratio of the variance
of the signal to the total variance is .82 for men and .92 for women.
These ratios fall to .65 and .81 when the data are specified in first
differences. Longitudinal earnings data may be more reliable than
previously believed.
@article{bound1991extent,
abstract = {This article examines the properties and prevalence of measurement
error in longitudinal earnings data. The analysis compares matched
Current Population Survey data to administrative Social Security
payroll tax records. In contrast to typically assumed properties
of measurement error, the results indicate that errors are serially
correlated over 2 years and negatively correlated with true earnings
(i.e., mean reverting). In a cross section, the ratio of the variance
of the signal to the total variance is .82 for men and .92 for women.
These ratios fall to .65 and .81 when the data are specified in first
differences. Longitudinal earnings data may be more reliable than
previously believed.},
added-at = {2017-11-27T13:59:49.000+0100},
author = {Bound, John and Krueger, Alan B.},
biburl = {https://www.bibsonomy.org/bibtex/2dcf2823b4007a11e9ffbbcce3a618ac6/dirtyhawk},
file = {:Bound_Krueger_1991.pdf:PDF},
interhash = {89c3ca45a2c756ac2605b9bf9769d773},
intrahash = {dcf2823b4007a11e9ffbbcce3a618ac6},
issn = {0734306X},
journal = {Journal of Labor Economics},
keywords = {socdes},
number = 1,
pages = {1-24},
timestamp = {2018-09-19T18:10:30.000+0200},
title = {The Extent of Measurement Error in Longitudinal Earnings Data: Do
Two Wrongs Make a Right?},
url = {http://www.jstor.org/stable/2535111},
volume = 9,
year = 1991
}