This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: 1 In-class Practice 5 NAME: _______________________________________________________ BUAD 310 USC ID# :__________________________________________________________ Friday Lab time :___________________________________________________ Dr. ANSARI PART 1 - MULTIPLE CHOICE [5 points each] 1. In regression analysis, the variance of error, is given by, a) MSR b) (SST-SSR) / DFE c) MST-MSR d) (SST-SSE) / DFE e) None of the above 2. The test for homoscedaticity is used in Regression to test for a) Non normality of Errors b) Constant standard deviation for Errors c) Correlation between Predictor and Errors d) Correlation between Errors e) None of the above 3. Conducting a Durbin-Watson test would be a good procedure for evaluating, a) Heterscedasticity b) Coefficient of determination c) Multicollinearity d) Autocorrelation e) None of the above 4. In a multiple regression problem with 15 predictor variables and 80 observations, degrees of freedom for regression and total would be, respectively, a) 13 and 79 b) 14 and 65 c) 14 and 79 d) 13 and 65 e) None of the above 5. One of the required conditions of regression analysis is that the variance of the error variable be a fixed value (constant). When this requirement is satisfied, the condition is called: a) Heterscedasticity b) Coefficient of determination c) Multicollinearity d) Autocorrelation e) None of the above 6. In multiple linear regression analysis, the Null hypothesis that the model is not useful can be tested using: 2 a) Both t-distribution and F-distribution b) Only F- distribution c) Only t-distribution d) None of the given distributions. 7. In regression analysis, the sample coefficient of determination R-sq is always, a) An unbiased estimator of the true coefficient of determination. b) Increases as the number of predictor variables decreases. c) Larger than R-sq adjusted. d) Measures variability in X explained by variability in Y. e) None of the above 8. Examining the correlation matrix of the independent variables would be a good procedure for evaluating, a) Heterscedasticity b) Coefficient of determination c) Multicollinearity d) Autocorrelation 9. In multiple regression Y-hat = hat + 1 hat X 1 + 2 hat X 2 , the interpretation of 2 hat is: a) The change in y for a one-unit change in X 2 b) The change in expected value of y for a one-unit change in X 2 c) The change in expected value of y for a one-unit change in X 2 , holding X 1 at constant value d) The change in expected value of y for a one-unit change in X 1 , holding X 2 at constant value 10. A study found Coefficient of Determination R-sq = 0.61 between the GPA of a worker and his or her income. From this you can conclude that: a) As GPA increases the income increases by 0.61 units....
View Full Document
- Summer '07