Refer to the data in Problem 19 of Chapter 5. The relationship between the rate of owner occupancy of housing units (OWNEROCC) and the median monthly ownership costs (OWNCOST) was studied in that problem in connection with a random sample of data from 26 Metropolitan Statistical Areas (MSAs). The results of the regression of OWNEROCC on OWNCOST and a third variable, the median household income (INCOME), are presented next.
Use the output given here and in Problem 19 of Chapter 5 to answer the following questions.
a. Test whether OWNCOST and INCOME, taken together, significantly help to predict the rate of owner occupancy.
b. Test whether OWNCOST is associated with the rate of owner occupancy after taking into account the contribution of INCOME.
c. Test whether INCOME is associated with the rate of owner occupancy after taking into account the contribution of OWNCOST.
d. Should INCOME be included in the model to control for confounding? Explain your answer, including discussion of any assumptions you made in reaching your answer.

Regression of OWNEROCC on OWNCOST and INCOME DF Sum of Squares Mean Square F Vatue Pr > F Source Model Error Corrected Total 2 214.4833906 23 386.4781479 25 600.9615385 638 0.0062 107 2416953 16.8033977 R-Square Coeff Var Root MSE Y Mean .356900 6.214523 4.099195 69.96154 Source OWNCOST INCOME DFI Type ISS | Mean Square | FValue! Pr>F 7.89 00100 4.87 0.0375 132.6203242 132.603242 1 81.8630664 81.8630664 DF Type III SS Mean Square F ValuePr> F Source OWNCOST INCOME 192.6978217 92 6978217 11.47 0.0025 1 81.8630664 81 8630664487 00375 Estimate | Standard Error | t Value | Pr 70.03201034 Parameter Intercept OWNCOST INCOME 5.37 0.0001 4.55666725 0.00984532 339 0.00029217221 .0375 0.03334031