longitudinal data


This paper performs a longitudinal comparison of public and
private sector pay. Although not decisive because of small sample
sizes, the results tend to corroborate the conclusions of previous
cross-sectional studies. Specifically, I find that on average
wages of federal workers exceed those of private sector workers by
10% to 25%, while wages of state and local government workers are
roughly equivalent to or slightly less than the wages of private
sector workers. Furthermore, these conclusions hold for a sample
of workers who joined the government after being involuntarily
displaced from their private sector jobs. In addition, a
comparative analysis of the length of job queues suggests that on
average more workers apply for job openings in the federal
government than in the private sector.
Finally, both longitudinal and cross-sectional analyses support
the conclusion that the union wage gap is substantially smaller in
the public sector than in the private sector.

Year of Publication
Date Published
Publication Language
Citation Key
In Richard Freeman and B. Casey Ichniowski (eds.), When Public Sector Workers Unionize, (Chicago: The University of Chicago Press, 1988), pp 217-240
Krueger, A. (1987). Are Public Sector Workers Paid More Than Their Alternative Wage? Evidence from Longitudinal Data and Job Queues. Retrieved from http://arks.princeton.edu/ark:/88435/dsp01t148fh13b (Original work published September 1987)
Working Papers

This paper examines the properties and prevalence of measurement
error in longitudinal earnings data. The analysis compares Current
Population Survey data to administrative Social Security payroll tax
records for a sample of heads of households over two years. In contrast
to the typically assumed properties of measurement error, the results
indicate that errors are serially correlated over two years and
negatively correlated with true earnings (i.e., mean reverting).
Moreover, reported earnings are more reliable for females than males.
Overall, 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. The estimates suggest that
longitudinal earnings data may be more reliable than previously believed.

Year of Publication
Date Published
Publication Language
Citation Key
Journal of Labor Economics, Vol 9, no 1, January 1991.
Bound, J., & Krueger, A. (1988). The Extent of Measurement Error in Longitudinal Earnings Data: Do Two Wrongs Make a Right?. Retrieved from http://arks.princeton.edu/ark:/88435/dsp01h989r321w (Original work published October 1988)
Working Papers