[R-SIG-Finance] Granger Causality Test

[Eric Zivot]

Granger causality only makes sense between stationary variables or between
nonstationary variables that are cointegrated. See the excellent textbook A
New Introduction to Multiple Time Series  by Helmut Lutkepohl for everything
you ever wanted to know about causality testing
 

-----Original Message-----
From: r-sig-finance-bounces at stat.math.ethz.ch
[mailto:r-sig-finance-bounces at stat.math.ethz.ch] On Behalf Of Hsiao-nan
Cheung
Sent: Wednesday, August 13, 2008 2:24 PM
To: R-SIG-FINANCE
Subject: [R-SIG-Finance] Granger Causality Test

Hi,

 

I have some question that whether only stationary series could do Granger
Causality Test. Is there any exception?

 

Since I!/ve found somewhere that to make a time series stationary, the
differential series may has little economic meaning.

 

Hsiao-nan Cheung

 

 


	[[alternative HTML version deleted]]