Use this URL to cite or link to this record in EThOS:
Title: Econometric bias and the estimation of male-female earnings differentials
Author: Skatun, Diane
ISNI:       0000 0001 2410 9519
Awarding Body: University of Aberdeen
Current Institution: University of Aberdeen
Date of Award: 1998
Availability of Full Text:
Access from EThOS:
This thesis looks at the empirical implementation of human capital theory in the form of the estimation of earnings functions for married males and females. Its main purpose is to investigate how any biases in estimation may affect males and females to different extents and thus lead to an inaccurate comparison between the two groups. It concentrates on the two productivity traits of education and experience. As such, it does not intend to provide a comprehensive account of male-female wage differentials, but looks instead at how any asymmetry of bias may feed through to measures of discrimination. This asymmetry in bias will, if uncorrected, give a false comparison of the two different groups' relative returns to schooling and experience. It is, as such, a cautionary tale which argues for the careful implementation of econometric techniques to earnings functions. A failure to correct for any asymmetry is likely to lead to inappropriate policy recommendations and may lead to inefficiency of policy in three potential and mutually exclusive ways. First, biases may artificially create differences between males and females where there are none, thus leading to the introduction of policy where inaction may be preferable. Second, biases may mask underlying differences, causing inappropriate inaction by government where action would indeed be merited. Third, biases may cause inaccurate measures of the relative returns to both education and experience and thus indicate falsely where it would be the most effective to target policy to reduce discrimination. This thesis has shown that, in order to suggest appropriate policy measures, so as to correctly introduce, implement and target policy, there is a need to apply appropriate econometric techniques and correct for biases.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: Gender; Inequality