Lecture 18 The Asymptotic variance of OLS and heteroskedasticity

Lecture 18 The Asymptotic variance of OLS and heteroskedasticity

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Economics 326 Methods of Empirical Research in Economics Lecture 18: The asymptotic variance of OLS and heteroskedasticity Vadim Marmer University of British Columbia March 24, 2009
Background image of page 1

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

View Full DocumentRight Arrow Icon
Asymptotic normality I In the previous lecture, we showed that when the data are iid and the regressors are exogenous: Y i = β 0 + β 1 X i + U i , EU i = E ( X i U i ) = 0 , the OLS estimator of β 1 is asymptotically normal: p n ˆ β 1 , n β 1 ± ! d N ( 0 , V ) , V = E ² ( X i EX i ) 2 U 2 i ³ ( Var ( X i )) 2 . I For the purpose of hypothesis testing, we need to obtain a consistent estimator of the asymptotic variance V : ˆ V n ! p V . 1/14
Background image of page 2
Homoskedastic errors I E U 2 i j X i ± = σ 2 for all X i I In this case, the asymptotic variance can be simpli±ed using the Law of Iterated Expectation: E ² ( X i EX i ) 2 U 2 i ³ = EE h ( X i EX i ) 2 U 2 i j X i i = E ² ( X i EX i ) 2 E ´ U 2 i j X i µ ³ = E ² ( X i EX i ) 2 σ 2 ³ = σ 2 E ( X i EX i ) 2 = σ 2 Var ( X i ) . 2/14
Background image of page 3

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

View Full DocumentRight Arrow Icon
I Thus, when the errors are homoskedastic with EU 2 i = σ 2 , V = E ( X i EX i ) 2 U 2 i ± ( Var ( X i )) 2 = σ 2 Var ( X i ) ( Var ( X i )) 2 = σ 2 Var ( X i ) . I Let ˆ U i = Y i ˆ β 0 , n ˆ β 1 , n X i , where ˆ β 0 , n and ˆ β 1 , n are the OLS estimators of β 0 and β 1 . I A consistent estimator for the asymptotic variance can be constructed by using the Method of Moments . ˆ σ 2 n = 1 n n i = 1 ˆ U 2 i , d Var ( X i ) = 1 n n i = 1 ( X i ¯ X n ) 2 , and ˆ V n = ˆ σ 2 n 1 n n i = 1 ( X i ¯ X n ) 2 . 3/14
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 03/24/2012 for the course ECON 326 taught by Professor Whisler during the Spring '10 term at UBC.

Page1 / 15

Lecture 18 The Asymptotic variance of OLS and heteroskedasticity

This preview shows document pages 1 - 5. Sign up to view the full document.

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