Julie Melamud
PAM 310
Homework #2
February 27, 2008
1.
log(wage)= β
0
+ β
1
educ + β
2
exper + β
3
tenure
log(wage)= 0.284 + 0.0920educ + 0.0041exper + 0.0221tenure
b. Interpret estimated coefficients:
•
Estimated β
1
 If we increase education by one unit and hold the values of
experience and tenure fixed, then wage would increase by 9.2%
(0.092x100%).
•
Estimated β
2

If we increase experience by one unit, and the values of
education and tenure are held constant, then wage would increase by
0.41% (0.0041x100%).
•
Estimated β
3
 If we increase tenure by one unit, and hold the values of
education and experience fixed, then wage increases by 2.21%
(0.0221x100%).
c. The value of R
2
is 0.3160. This value implies that education, experience, and
tenure altogether can explain 31.6% of the variation in wages.
d. MLR 3 (No perfect collinearity) is the assumption that none of the independent
variables are constant and that there is no exact linear relationships among the
independent variables. This model DOES violate MLR 3 because if g(
exper
)= 2 x
exper
, then
g(exper)
is a constant multiple of
exper,
and there is an exact linear
relationship between the variables. Therefore, the model suffers from perfect
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 '08
 ABDUS,S.
 Regression Analysis, Salary, higher starting salary

Click to edit the document details