1. Using annual data for the US. manufacturing sector for 1899 1922, Dougherty o
ID: 3044910 • Letter: 1
Question
1. Using annual data for the US. manufacturing sector for 1899 1922, Dougherty obtained the In Y= 2.81. -0.53 In K +0.9 1 In L + 0.047 t R" = 0.97, F=189.8 where Y index of real output. K index of real capital input, L index of real labour input, t time following regression results; KOR iven in parentheses, Using the same data, he also obtained the following regression ln(Y/L)-·-0.1.*+0.11m(K)L)-00061 0.11+0, 1 1 In (K/L)+0006t 03 15) th + R2 R-0.65, F=19.5 01i06 a) Is here multicollinearity in the f Ink? Do the results conform to this expectation? Why or why not? What are the consequences of imperfect multicollinearity? irst regression? How do you know? What is the a priori sign off b) Interpret the irst regression. What is the role of the trend variable in this regression? c) What is the logic behind estimating the second regression? d) II there was multicollinearity in the first regression, has that been reduced by the second regression? How do you know? l..1 1 1 e) Are the R values of the two regressions comparable? Why or Why nol? How would you make them comparabls. if they are nol comparable in the present form?Explanation / Answer
Yes, multicollinearity present in the first model.
Multicollinearity can be detect by using the variance inflation factor (V.I.F).
If V.I.F. > 10 the chances of multicollinearity.
V.I.F.1 = 1 / (1-R^2)
= 1 / (1-0.97)
= 33.333333 > 10 I.e. Multicollinearity present in model.
V.I.F.2 = 1 / (1-R^2)
= 1 / (1-0.65)
= 2.85414285 < 10 I.e. No chances Multicollinearity.
In Model one If trend increases by one unit then real output increases by 0.047 times. and if labour input increases by one unit then real output increases by 0.91 times and if real capital increses by one unit then real output decreases by 0.53 times.
Second Regression equation is regarding to quadratic regression equation using this we can reduce the variation of the regression equation i.e also decrease in multicollinearity.
We can not decide directly the model good or bad directly usig the R^2 because if we increase the variable in model then R^2 also increase so use Adj R^2 to give decision.
>>>>>>>>>>>>>>>> Best Luck >>>>>>>>>>>>>>>>>
Related Questions
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.