metricsexam2s08sol

metricsexam2s08sol - Econometrics Exam 2 April 29, 2008 By...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Econometrics Exam 2 By writing your PID below, you are indicating April 29, 2008 your intention to abide by the honor pledge: PID: This exam consists of ten short questions ( worth four points apiece ) and five long questions ( worth twelve points each ) , for a total of 100 points. You have 120 minutes to answer all completely and clearly in the space provided. Short Questions 1. What is the advantage of using instrumental variables, relative to OLS, and what is the disadvantage? IV is unbiased, regardless of whether the explanatory variables are endogenous. However, it is less efficient than OLS. 2. What would cause the first - difference and fixed - effects estimators to give substantially different results? A failure of “strict exogeneity” causes both estimators to be biased, but biased in different ways so in this case, we would expect FD and FE to give different results. 3. When estimating a system of equations, what would determine whether you use “seemingly unrelated regression” or “three - stage least squares”? SUR is appropriate when all the explanatory variables are exogenous; 3SLS is appropriate when ( some of ) the explanatory variables are endogenous.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
What does it mean for an estimator to be “unbiased”? E [ ˆ ! ] = 5. List three tests you should perform, if possible, after estimating a model using instrumental variables. The Hausman test; the test for overidentification ( if possible ) , and the test for weak instruments. 6. State the assumptions of the OLS model. E [ ! X e ] = 0 ! X X is invertible E [ e ! e ] = " 2 I 7. When does “simultaneity bias” arise, and what technique ( s ) can eliminate the bias? Simultaneity bias occurs when using OLS in a situation where y 1 is determined in part by y 2 , and y 2 is determined in part by y 1 ( in other words, when causality goes in both directions ) . 2SLS or 3SLS can yield unbiased estimates.
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 03/19/2010 for the course ECON 570 taught by Professor Staff during the Spring '08 term at UNC.

Page1 / 8

metricsexam2s08sol - Econometrics Exam 2 April 29, 2008 By...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online