[R] how to study the lead and lag relation of two time series?

Jeffrey J. Hallman jhallman at frb.gov
Fri Jan 23 15:40:48 CET 2009


Yes, it's called Ocular Econometrics.  You plot both series on the same chart
and use your onboard pattern detector.  If you can't see it on the plot, it's
unlikely that any correlations you find in other ways will have much
predictive power, and that's the only kind of relationship that counts.

I know you asked for a systematic way to do this, but at least with economic
time series, experience tells me that correlations that can't be seen with the
naked eye are rarely meaningful.

I'm now ready to duck all the brickbats that are about to come my way.

Jeff


Michael <comtech.usa at gmail.com> writes:
> Hi all,
>
> Is there a way to study the lead and lag relation of two time series?
>
> Let's say I have two time series, At and Bt. Is there a systematic way
> of concluding whether it's A leading B or B leading A and by how much?
>
> Thanks!
>

-- 
Jeff




More information about the R-help mailing list