B2)
Consider the following wage equation that has been estimated from a sample
of 3565 year old older male workers in a single large company:
Dependent variable: ln wage
(1)
(2)
(3)
Constant
3.825
3.441
3.582
12.10
12.11
12.04
Age
0.154
0.155
0.148
3.18
2.11
1.98
Age
2
0.014
0.013
0.014
1.55
2.04
2.03
NT

0.0091
0.0064
4.11
3.90
NT
2

0.0094
0.0026
3.91
3.27
NT
3

0.0006
0.0001
4.06
3.84
EDUC
0.183

0.122
5.08
6.61
No of obs
4823
4823
4823
R
2
0.104
0.221
0.240
where Age is Age in years divided by 10; NT is a variable indicating the total number
of days of training courses workers have taken over their career and EDUC is a
dummy variable indicating if the individual has higher education qualifications.
Numbers in italics are absolute tratios.
a) Taking the specification in column (1), at what age are wages predicted to be
highest? Is there statistically significant evidence of declines in wages with age after
this point?
b) Use the table above to test the hypothesis that the returns to higher education
estimated in model (1) are 10%.
c) Considering equation (2), what evidence do the estimates provide on the nature of
returns to training? At what level of training are returns to training at their maximum?
d) In what circumstances would the estimator of the returns to training you derived in
part (c) be a biased estimate of the true effect? Give at least one example that could
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '09
 matthewwakefield
 Economics, Statistics, Matthew Wakefield

Click to edit the document details