This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Applied Econometrics Final 13 th of December, 2005 This exam consists of ten short questions ( worth three points apiece ) and six long questions ( worth fifteen points each ) , for a total of 120 points. You have 120 minutes to answer all completely and clearly in the space provided. Short Questions 1. What does it mean that an estimator is consistent? 2. Why would it be bad to use OLS with censored data? 3. What is a natural experiment? 4. What is the purpose of the Hausman test? 5. What does an odds ratio tell you? 6. How would you test that your model is correctly specified? 7. What is the purpose of the test of overidentification? 8. When would you use the Poisson regression model? 9. What is attrition? 10. What is simultaneity bias? Question 1: Suppose that the model is y i = ! 1 + ! 2 " x i + e i ( the standard linear model with a single regressor ) . The following conditions are true: E ! x i ! e i " = , E !" x i x # 2 $ , and E !" e i ! e # 2 $ = " i 2 ( and generally...
View Full
Document
 Spring '08
 Staff
 Econometrics

Click to edit the document details