QUESTION

Consider the following two regressions based on the US data for 1946 to 1975 (standard errors are in parentheses)
Ct = 26.19 + 0.6248GNPt - 0.4398Dt
Se = (2.73)   (0.0068)           (0.0736)  R^2=0.999
(C/GNP) = 25.92 1/GNPt + 0.6246 - 0.4315 D/GNPt
           Se = (2.22)                (0.0068) (0.0597)
R^2 = 0.875
Where C = aggregate private consumption expenditure
GNP = gross national product
D = national defense expenditure
t = time
The objective of the study was to find out the effect of defense expenditure on other expenditures in the economy.
a. What might be the reason(s) for transforming the first equation into the second equation?
b. Based on the objective of the transformation, what assumption has been made about the error variance?
c. If there was a problem, have the authors succeeded in removing it? How can you tell?
d. Does the transform regression have to be run through the origin? Why or why not?
e. Can you compare the R^2 values of the two regressions? Why or why not?

Public Answer

F3PHIC The First Answerer