hw3 - ECN 725 Spring 2010 Q1. ASSIGNMENT 3 DUE April 16...

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

View Full Document Right Arrow Icon
1 ECN 725 ASSIGNMENT 3 S.C. AHN Spring 2010 DUE April 16 (Friday), 2:00pm Q1. (10 pts.) Consider a regression model 12 23 3 y xx u   , which satisfies all SIC. Assume that regressors are stochastic. Let 2 be the OLS estimator of 2 from the regression of t y on one and 2 t x (omitting 3 t x ). Show that: 22 , 3 , 2 cov( , ) lim var( ) To o x x p x   . Q2. (30 pts.) Consider the following model: y = 1 1 T + 2 w + u, where y, w and u = (u 1 , . .. , u T ) are all T 1 vectors and 1 T is a T 1 vector of ones. The vector w is nonstochastic. And all SIC hold except that var(u t ) = 2 and cov(u t ,u s ) = 2 ( < 1) for all t s. Define P(1 T ) = 1 T (1 T 1 T ) -1 1 T and M(1 T ) = I T - P(1 T ). (1) Show that Var(u) = 2 , where = (1- )M(1 T ) + (1- + T)P(1 T ). (2) Let s 2 = SSE/(T-2), where SSE is from the OLS estimation of the model. Find E(s 2 ). (3) Let 2 be the GLS estimator of 2 . Show that ˆ . [Hint: 1 11 (1 ) TT MP T    .] Q3. (10 pts.) In the regression model o y Xu , X
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

hw3 - ECN 725 Spring 2010 Q1. ASSIGNMENT 3 DUE April 16...

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