4. Heteroskedasticity and Serial Correlation Suppose you estimate the following time series regression: qoil,td=+oilpoil,t+poppopt+ where qoil,td is the quantity demanded of oil, poil,t is the price of oil, and popp is population (in millions). The results from this regression are shown in the table below. 7. After estimating the above model, you are worried that the model may suffer from heteroskedasticity. Based on the following graph of the residuals (error term) and population, do you think the model suffers from heteroskedasticity (i.e., does it look like the variance of the error term is non-constant)? Regardless of your answer to (7.), you decide to conduct a Breusch-Pagan test. To do so, you estimate the model ^t2=+oilpoil,t+pop pop t+v, where ^t2 are the squared residuals from the original regression model. 8. What is the test statistic, nR2, equal to if n=47 and R2=0.5408 ? 9. The P-value associated with the test statistic, nR2, is 0.000. Are you able to reject the null hypothesis of homoskedasticity, H0:var(i)=2, at the 10% level? 4. Heteroskedasticity and Serial Correlation Suppose you estimate the following time series regression: qoil,td=+oilpoil,t+poppopt+ where qoil,td is the quantity demanded of oil, poil,t is the price of oil, and popp is population (in millions). The results from this regression are shown in the table below. 7. After estimating the above model, you are worried that the model may suffer from heteroskedasticity. Based on the following graph of the residuals (error term) and population, do you think the model suffers from heteroskedasticity (i.e., does it look like the variance of the error term is non-constant)? Regardless of your answer to (7.), you decide to conduct a Breusch-Pagan test. To do so, you estimate the model ^t2=+oilpoil,t+pop pop t+v, where ^t2 are the squared residuals from the original regression model. 8. What is the test statistic, nR2, equal to if n=47 and R2=0.5408 ? 9. The P-value associated with the test statistic, nR2, is 0.000. Are you able to reject the null hypothesis of homoskedasticity, H0:var(i)=2, at the 10% level