This paper investigates the goodness‐of‐fit' and effect on estimates of the experience‐earnings profile of alternative specifications of the human capital earnings function for a sample of full‐time male workers in Australia. It is concluded that it is difficult to differentiate between specifications of the earnings function which include a cubic experience term, cubic plus quartic experience terms, or a linear spline function in experience–each of these specifications appears to marginally dominate the quadratic specification and a non‐parametric approach. A modified Gompertz function is found to perform poorly.
No takes yet. Share an insight, caveat, or question.
Borland et al. (1994) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: