EC30920IntroductiontoEconometricsResitPaper.docVIP

EC50161 Financial Econometrics Specimen Exam paper Answer Three questions Time allowed: TWO hours 1a) Describe the steps involved in running an OLS regression from the initial point of deciding the theoretical model to stating the conclusions on the results.{50%] A researcher obtained the following ordinary least squares (OLS) estimates for a UK firm’s stock price using 120 observations from 1980 m1 to 1989m12 (All variables in logarithms): st are the log of the stock price, pt is the log of profits, yt is the log of its output in the UK, rt is the log of expenditure on research and development and mt is the log of expenditure on Marketing. Figures in parentheses are standard errors and RSS is the Residual Sum of Squares. Briefly evaluate the reasons behind including the above explanatory variables in the regression. [10 %] What is the explanatory power of the regression? [15 %] Individually using the t-test, test whether each coefficient equals 0, at the 5% level of significance [15%] Using a t-test does the coefficient on the variable lnyt = 1? [10%] An investigator estimated the parameters in the equation by Ordinary Least Squares using 52 quarterly observations for 1972 to 1984 inclusive. This resulted in a residual sum of squares (RSS) of 0.78. When 3 dummy variables representing the first 3 quarters of the year were added to the equation the RSS fell to 0.56. Using an F-test, test for the presence of seasonality stating what assumptions are being made concerning the form of the seasonality. [25%] When 5 lagged values of lnX were added to the original equation (without the dummy variables), without reducing the number of observations used in the estimation, the RSS fell to 0.45. Test the joint significance of these five extra variables [25%] Briefly explain how an F-test can be used to test the constant returns to scale restriction in the Cobb-Douglas production function? [50%] 3) i) Explain why the error term needs to be normally di