This preview shows pages 1–6. 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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Lecture 12 : Multicollinearity, Heteroskedasticity Econ 444, Winter 2010 Feb 23, 2010 How to detect Multicollinearity ? 1 High R 2 but few significant tratios may suggest presence of multicollinearity. 2 High pairwise correlations among explanatory variables. 3 Variance Inflation Factor (VIF) : measures how much multicollinearity has increased the variance of an estimated coefficient. For example, consider the following regression equation, Y i = + 1 X 1 i + 2 X 2 i + 3 X 3 i + i (1) Now to compute the VIF corresponding to say estimate of 1 we follow two steps: 1 Estimate the following equation and save the R 2 1 : X 1 = 1 + 2 X 2 + 3 X 3 + i (2) 2 Then the VIF for 1 is given by, VIF ( 1 ) = 1 1 R 2 1 (3) Similarly to obtain VIF corresponding to 2 , 1 Estimate the following equation and save the R 2 2 : X 2 = 1 + 2 X 1 + 3 X 3 + i (4) 2 Then the VIF for 1 is given by, VIF ( 2 ) = 1 1 R 2 2 (5) Few things to note : There will be a VIF for every coefficient estimated in the equation. So in previous example, there will be 3 VIFs....
View
Full
Document
This note was uploaded on 04/13/2010 for the course ECON 444 taught by Professor Ogaki during the Winter '07 term at Ohio State.
 Winter '07
 OGAKI
 Econometrics

Click to edit the document details