The following table shows the results of a regression that estimate the average fuel efficiency (kilometre...

  

Transcribed Image Text:

The following table shows the results of a regression that estimate the average fuel efficiency (kilometre per litter) of 53 different passenger cars using the size of engine (displacement in cubic centimetres) and weight of the car (in 100 kilograms) as independent variables. (c) (d) Model 1: OLS, using observations 1-53 Dependent variable: kml (e) const disp weight (f) Coefficient P-values (2-tailed test) 32.231 0.0159 -0.0549 0.0115 -0.4659 0.0716 The variables are defined as follows: "kml' - fuel efficiency in kilometre per litre, 'disp' - displacement of the engine in cubic centimetres, 'weight' - weight of the car in 100 kilograms. (a) Interpret the estimated coefficient of 'disp'. Sum squared resid R-squared [5 marks] (b) Test, at the 5% significance level, whether heavier cars have lower fuel efficiency. State the null and alternative hypotheses clearly. 229.5785 0.742975 S.E. of regression 1.715609 Adjusted R-squared 0.728948 [5 marks] Conduct an F-test for overall significance of the above regression model at the 5% significance level. State the null and alternative hypotheses clearly. [8 marks] Would you expect the variance of error terms in the above regression model to be homoscedastic (constant)? Explain. [5 marks] Using the squared residuals (uhat^2) obtained from the estimation of the original regression as the dependent variable, an auxiliary regression was estimated to conduct a White's general test. The adjusted R-squared of the auxiliary model is 0.2239. Conduct the test for heteroscedasticity at the 1% significance level. State the null and alternative hypotheses clearly. [6 marks] Explain, with an appropriate example, how a Weighted Least Square method can be used to overcome the problem of heteroscedasticity. [6 marks] The following table shows the results of a regression that estimate the average fuel efficiency (kilometre per litter) of 53 different passenger cars using the size of engine (displacement in cubic centimetres) and weight of the car (in 100 kilograms) as independent variables. (c) (d) Model 1: OLS, using observations 1-53 Dependent variable: kml (e) const disp weight (f) Coefficient P-values (2-tailed test) 32.231 0.0159 -0.0549 0.0115 -0.4659 0.0716 The variables are defined as follows: "kml' - fuel efficiency in kilometre per litre, 'disp' - displacement of the engine in cubic centimetres, 'weight' - weight of the car in 100 kilograms. (a) Interpret the estimated coefficient of 'disp'. Sum squared resid R-squared [5 marks] (b) Test, at the 5% significance level, whether heavier cars have lower fuel efficiency. State the null and alternative hypotheses clearly. 229.5785 0.742975 S.E. of regression 1.715609 Adjusted R-squared 0.728948 [5 marks] Conduct an F-test for overall significance of the above regression model at the 5% significance level. State the null and alternative hypotheses clearly. [8 marks] Would you expect the variance of error terms in the above regression model to be homoscedastic (constant)? Explain. [5 marks] Using the squared residuals (uhat^2) obtained from the estimation of the original regression as the dependent variable, an auxiliary regression was estimated to conduct a White's general test. The adjusted R-squared of the auxiliary model is 0.2239. Conduct the test for heteroscedasticity at the 1% significance level. State the null and alternative hypotheses clearly. [6 marks] Explain, with an appropriate example, how a Weighted Least Square method can be used to overcome the problem of heteroscedasticity. [6 marks]

Answer rating: 100% (QA)

a Interpret the estimated coefficient of disp 5 marks The estimated coefficient of disp is 00549 This suggests that for a given weight a one unit increase in engine displacement in cubic centimetres i... View the full answer