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: Midterm 2 - Spring 2010 - Form C Economics 203 Instructors: Petry and Sahakyan Name: Before beginning the exam, please verify that you have 16 pages with 43 questions in your exam booklet. You should also have a decision-tree and formula sheet provided to you. Please include your full name and Net-ID on your bubble sheets. Based on the name of your TA and discussion time, please code in the following for the Section portion on your scantron: TA Name Discussion Day and Time Section Josh Brown Thursday 9am 001 Josh Brown Thursday 10am 002 Josh Brown Thursday 11am 003 Rafael Ribas Thursday 12pm 004 Rafael Ribas Thursday 1pm 005 Rafael Ribas Thursday 2pm 006 Andreas Hagemann Friday 8am 007 Andreas Hagemann Friday 9am 008 Andreas Hagemann Friday 10am 009 Sergey Popov Friday 11am 010 Sergey Popov Friday 12pm 011 Sergey Popov Friday 1pm 012 Esra Ergul Friday 11am 013 Esra Ergul Friday 12pm 014 Esra Ergul Friday 1pm 015 Lusha Zhu Friday 2pm 016 Lusha Zhu Friday 3pm 017 Lusha Zhu Friday 4pm 018 Good luck! 1. Which of the following statements best describes positive autocorrelation? a. The distribution of the residuals is skewed, so that it does not resemble a bell-shaped curve b. The absolute size of the residuals is related to the value of the dependent variable c. Two or more of the independent variables have a high correlation d. Consecutive residuals are likely to have the opposite sign, one positive and one negative e. Consecutive residuals are likely to have the same sign, either both positive, or both negative 2. Which of the following statements are correct with regard to the coefficient of determination and the adjusted coefficient of determination? a. Adjusted coefficient of determination can never be less than zero while the coefficient of determi- nation can have a negative value b. Coefficient of determination can have values between -1 and 1. c. Coefficient of determination will be penalized if we use too many independent variables in a regres- sion model. d. Coefficient of determination can never decrease when we introduce more independent variables into a regression model. e. Adjusted coefficient of determination can never decrease when we include more independent vari- ables into a regression model. 1 3. The value of R 2 for your linear model is 0, with n=50, k=4, and SST=50,000. What is the value of the F-statistic? a. 0. b. + . c. Unknown; need parameter values. d. Unknown; need SSE and SST. e. Unknown; need amount of variables. 4. Which of the following is false with regards to the effects of serious multicollinearity? a. the overall F-test may indicate a valid model but the individual t-tests indicate none of the inde- pendent variables are linearly related to the dependent variable b. confidence intervals on estimated slope parameters are larger c. a reduced p-value for the individual t-tests d. an increased standard error of the individual slope coefficients e. a decrease in the absolute value of the individual t-test test statisticse....
View Full Document
- Spring '09