725_sample exam_2_answer_2010

725_sample exam_2_answer_2010 - Key Answers for Exercise 2:...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Key Answers for Exercise 2: Q1: (1) Do not agree (DNA). When important regressors are omitted, OLS estimator becomes inconsistent. (2) DNA. As long as WIC hold and T is large, OLS is consistent and asymptotically normal. (3) DNA. Dropping regressors may cause omitted-variables biases. (4) DNA. We can estimate the OLS covariance matrix using the Newey-West method. With this covariance matrix and OLS estimator of β , we can do test any hypothesis about . (5) DNA. We can use R 2 for model comparison only if the models to be compared use the same dependent variable. Q2: ˆ var( ) 1. Q3: (1) i) Use (B) to test for heteroskedasticity: Koenker’s test = T R 2 = 30 > 3.84 = c from χ 2 (1) at 95%. ii) Use GLS for random coefficient models (See the class notes for detailed estimation procedure). (2) Use (C): LM-type test = T R 2 = 5 > 3.84 = c from 2 (1). (3) Do the Prais-Winston GLS: Using (D), we can obtain ˆ = 0.4. Using this value, do the Prais-Winston transformation. Then, estimate the transformed equation by OLS.
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/19/2010 for the course ECON 270a taught by Professor Ahn during the Spring '10 term at ASU.

Page1 / 2

725_sample exam_2_answer_2010 - Key Answers for Exercise 2:...

This preview shows document pages 1 - 2. Sign up to view the full document.

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