Econ 262 In-class Assignment on Heteroskedasticity 1. Run an OLS regression with Y as the dependent variable and X 1 and X 2 as the independent variables. SAVE THE RESIDUALS. Make a scatterplot of X 2 versus the residuals, with the residuals on the vertical axis. Does the residual analysis suggest heteroskedasticity? Observe the p-values. Do any of the p-values suggest heteroskedasticity? (Note: looking for a “cone shape” in the relationship between the residuals and X 2 ) 2. Perform a White test of heteroskedasticity. State the null and alternative hypotheses, the decision rule and inference. Recall: Step 1: run regression with Y as the dependent variable and X 1 and X 2 as independent variables and save the residuals (NOTE: ALREADY DONE IN QUESTION 1). Step 2: Create new dataset where var(e)=residual^2, X 1 , X 1 ^2, X 2 , X 2 ^2, and X 1 X 2 . Step 3: Run regression based on data in step 2 with var(e) as the dependent variable. Step 4:
This is the end of the preview. Sign up
access the rest of the document.
This note was uploaded on 06/23/2011 for the course ECON 261 taught by Professor Williamrobinson during the Spring '11 term at AIB College of Business.