Use the data in FERTIL2.RAW to answer this question. 

(i) Estimate the model and report the usual and heteroskedasticity-robust standard errors. Are the robust standard errors always bigger than the nonrobusl ones? 

(ii) Add the three religious dummy variables and test whether they are jointly significant. What are the p-values for the non-robust and robust tests?

(iii) From the regression in part (ii), obtain the fitted values ŷ and the residuals, û. Regress û ² on ŷ, ŷ ₂ and the test the joint significance of the two regressions. Conclude that heteroskedasticity is present in the equation to children.

(iv) Would you say the heteroskedasticity you found in part (iii) is practically important? 

 

children = B, + Bage + Bage? + Bzeduc + B,electric + Bzurban + u