Table 11.10 from the website gives salary and related data on 447 executives of Fortune 500 companies. Data include salary = 1999 salary and bonuses; totcomp = 1999 CEO total compensation; tenure = number of years as CEO (0 if less than 6 months); age = age of CEO; sales = total 1998 sales revenue of the firm; profits = 1998 profits for the firm; and assets = total assets of the firm in 1998.

a. Estimate the following regression from these data and obtain the Breusch– Pagan–Godfrey statistic to check for heteroscedasticity:

salaryi = β₁ + β₂ tenure_i + β₃ age_i + β₄ sales_i + β₅ profits_i + β₆ assets_i + u_i

Does there seem to be a problem with heteroscedasticity?

b. Now create a second model using ln(Salary) as the dependent variable. Is there any improvement in the heteroscedasticity?

c. Create scattergrams of salary vs. each of the independent variables. Can you discern which variable(s) is (are) contributing to the issue? What suggestions would you make now to address this? What is your final model?