Project #51366 - Econometrics GRETL

I. HETEROSKEDASTICITY

  1. In Dougherty, pp. 287-299, problems 7.1, 7.2, 7.5, 7.7, and 7.11.
    Computer problems: In GRETL to obtain heteroskedasticity-robust standard errors, (1) click on OLS, (2) check the robust standard error box on the lower left hand corner, and (3) estimate the model. The output will yield robust standard errors.
     
  2. a.Run an OLS model using the data set from Wooldridge: "htv"; Wages: returns to schooling.
    Regress lwage on a constant, abil, educ, exper, and expersq.

    b. Report the OLS standard errors and heteroskedasticity-robust standard errors. Explain the difference, if any, between the two types of estimated standard errors. Does it make a difference in the significance of the coefficients? Explain. Also report the p-values. Interpret your results, that is, what coefficients have a significant influence on wages?

    c. Use White's test to test for heteroskedasticty. (Note: After you run OLS, click on "tests", then click on "heteroskedasticity", and then click on White's test.

    d. Repeat using Breusch-Pagan test. Are there any differences in the test results between White's test and the Breusch-Pagan test? Explain.
     
  3. Repeat problem 2 using the Wooldridge data set: "beauty"; Physical attractiveness and earnings.
    Regress lwage on a constant, belavg, abvavg, exper., union, female, black, expersq2, and edu. Also, report whether "beauty" has a significant effect on wages. In addition, does being a female or black have a significant influence on wages? Explain.
     
  4. What is the difference between small-sample or exact test properties and asymptotic sampling properties? Note that many tests only have asymptotic properties.

II

  1. In Dougherty, p. 438, work problem 12.1.
     
  2. Computer problems: In Gretl, use the data set under Wooldridge, "consumption, income and interest rate" and
    1. Regress "c" (per capita real consumption) on "y" (per capita real disposable income) and "inf" (inflation rate, CPI) and obtain OLS estimates.
    2. Plot the residuals against time. What do you conclude by observing this plot? Is the plot consistent with the autocorrelation tests below?
    3. Test for the significance of individual coefficients and the overall goodness of fit Explain your results.
    4. Test for first-order autocorrelation using the Durbin-Watson statistic (Hint: Run OLS and click on "Tests" and report the D-W value and p-values that are given.
    5. Test for first-order autocorrelation using the Breusch-Godfrey test. Is there evidence for autocorrelation? Explain.
       
  3. Use the data set under Gretl, "unemployment and inflation" (Stock  Watson) and regress Unemployment (LHUR) against a constant and inflation (PUNEW). Repeat the steps a-e in question 2 for these data.
     
  4. Use the data set under Gretl, "theil" (Henri Theil's textile consumption data) and obtain OLS estimates. Repeat parts a-e under question 2 above for these data.
     
  5. Repeat question 2, but regress log(c) on log(y) and log( inf).
     
  6. Regress "c" on "y" and "inf" as in problem 2, and estimate the model by the Cochrane-Orcutt method (corrected for autocorrelation). What are the differences between the Cochrane-Orcutt estimates and the OLS estimates?

Subject Mathematics
Due By (Pacific Time) 12/11/2014 09:00 am
Report DMCA
TutorRating
pallavi

Chat Now!

out of 1971 reviews
More..
amosmm

Chat Now!

out of 766 reviews
More..
PhyzKyd

Chat Now!

out of 1164 reviews
More..
rajdeep77

Chat Now!

out of 721 reviews
More..
sctys

Chat Now!

out of 1600 reviews
More..
sharadgreen

Chat Now!

out of 770 reviews
More..
topnotcher

Chat Now!

out of 766 reviews
More..
XXXIAO

Chat Now!

out of 680 reviews
More..
All Rights Reserved. Copyright by AceMyHW.com - Copyright Policy