This preview shows page 1. Sign up to view the full content.
Unformatted text preview: P-value and your conclusion. 3. Using the model that fits two different lines, give a 95% confidence interval for the difference in slopes. (Hint: what parameter represents the difference between the slopes?) 4. For this problem use again the computer science dataset, and fit the model which uses only HSM and HSE as explanatory variables to predict the response GPA. Examine some additional diagnostics for this model that we recently discovered, such as studentized residuals, tolerance or vif, and possibly others. Explain any problems such as outliers, highly influential observations or multicollinearity that these diagnostics point out. ( Do not include in your output any tables of values for all 224 individuals. Use plots and verbal summaries instead. You may include values for a few selected individuals if you wish.)...
View Full Document
- Spring '08