The McGraw-Hill Series Economics essentials of economics brue, McConnell, and Flynn Essentials of Economics

Empirical Exercises
12.26. Refer to the data on the copper industry given in Table 12.7.
a.
From these data estimate the following regression model:
ln
C
t
=
β
1
+
β
2
ln
I
t
+
β
3
ln
L
t
+
β
4
ln
H
t
+
β
5
ln
A
t
+
u
t
Interpret the results.
b.
Obtain the residuals and standardized residuals from the preceding regression
and plot them. What can you surmise about the presence of autocorrelation in
these residuals?
c.
Estimate the Durbin–Watson 
d
statistic and comment on the nature of autocor-
relation present in the data.
d.
Carry out the runs test and see if your answer differs from that just given in (
c
).
e.
How would you find out if an AR(
p
) process better describes autocorrelation
than an AR(1) process?
Note:
Save the data for further analysis. (See Exercise 12.28.)
guj75772_ch12.qxd 14/08/2008 10:41 AM Page 460

---

Chapter 12
Autocorrelation: What Happens If the Error Terms Are Correlated?
461
12.27. You are given the data in Table 12.8.
a.
Verify that Durbin–Watson 
d
=
0.4148.
b.
Is there positive serial correlation in the disturbances?
c.
If so, estimate 
ρ
by the
i
. Theil–Nagar method.
ii
. Durbin two-step procedure.
iii
. Cochrane–Orcutt method.
d.
Use the Theil–Nagar method to transform the data and run the regression on the
transformed data.
e.
Does the regression estimated in (
d
) exhibit autocorrelation? If so, how would
you get rid of it?