Part One
Single-Equation Regression Models
9.23. Reestimate the model in Exercise 9.22 by adding the regressor, expenditure on
durable goods.
a.
Is there a difference in the regression results you obtained in Exercise 9.22 and in
this exercise? If so, what explains the difference?
b.
If there is seasonality in the durable goods expenditure data, how would you
account for it?
9.24. Table 9.9 gives data on quadrennial presidential elections in the United States from
1916 to 2004.
*
a.
Using the data given in Table 9.9, develop a suitable model to predict the
Democratic share of the two-party presidential vote.
b.
How would you use this model to predict the outcome of a presidential election?
*
These data were originally compiled by Ray Fair of Yale University, who has been predicting the out-
come of presidential elections for several years. The data are reproduced from Samprit Chatterjee, Ali
S. Hadi, and Bertram Price,
Regression Analysis by Example,
3d ed., John Wiley & Sons, New York,
2000, pp. 150–151 and updated from http://fairmodel.econ.yale.edu/rayfair/pdf/2006CHTM.HTM.
Obs.
Year
V
W
D
G
I
N
P
1
1916
0.5168
0
1
2.229
1
3
4.252
2
1920
0.3612
1
0
−
11.46
1
5
16.535
3
1924
0.4176
0
−
1
−
3.872
−
1
10
5.161
4
1928
0.4118
0
0
4.623
−
1
7
0.183
5
1932
0.5916
0
−
1
−
14.9
−
1
4
7.069
6
1936
0.6246
0
1
11.921
1
9
2.362
7
1940
0.55
0
1
3.708
1
8
0.028
8
1944
0.5377
1
1
4.119
1
14
5.678
9
1948
0.5237
1
1
1.849
1
5
8.722
10
1952
0.446
0
0
0.627
1
6
2.288
11
1956
0.4224
0
−
1
−
1.527
−
1
5
1.936
12
1960
0.5009
0
0
0.114
−
1
5
1.932
13
1964
0.6134
0
1
5.054
1
10
1.247
14
1968
0.496
0
0
4.836
1
7
3.215
15
1972
0.3821
0
−
1
6.278
−
1
4
4.766
16
1976
0.5105
0
0
3.663
−
1
4
7.657
17
1980
0.447
0
1
−
3.789
1
5
8.093
18
1984
0.4083
0
−
1
5.387
−
1
7
5.403
19
1988
0.461
0
0
2.068
−
1
6
3.272
20
1992
0.5345
0
−
1
2.293
−
1
1
3.692
21
1996
0.5474
0
1
2.918
1
3
2.268
22
2000
0.50265
0
0
1.219
1
8
1.605
23
2004
0.51233
0
1
2.69
−
1
1
2.325
Notes:
Year Election year
V
Incumbent share of the two-party presidential vote.
W
Indicator variable (1 for the elections of 1920, 1944, and 1948, and 0 otherwise).
D
Indicator variable (1 if a Democratic incumbent is running for election,
−
1 if a Republican incumbent is running for election, and 0
otherwise).
G
Growth rate of real per capita GDP in the first three quarters of the election year.
I
Indicator variable (1 if there is a Democratic incumbent at the time of the election and
−
1 if there is a Republican incumbent).
N
Number of quarters in the first 15 quarters of the administration in which the growth rate of real per capita GDP is greater than 3.2%.
P
Absolute value of the growth rate of the GDP deflator in the first 15 quarters of the administration.
Do'stlaringiz bilan baham: |