Re: Reply to B. Mitchell, P. Davidson

[ACSLKS@xxxxxxxxxxxxxxxx id <01HN1BVOUE0W8Y71DC@xxxxxxxxxxxxxxxx>; Tue, 14 Feb 1995 11:21:35 -0400 (EDT)]

> Is this a counter-example? There is some evidence of 2 unit roots
> in prices and money. It is fairly easy to imagine a case where the
> real money supply has a unit root in it but inflation cointegrates
> with the money growth rate. --Alan G. Isaac
>
> On Mon, 13 Feb 1995 19:19:50 -0700       Lonnie K. Stevans said:
> >On your first point, of course you can cointegrate differenced series.  One can
> >also look for causality between liquor sales and the number of ordained
> >ministers.  My point is that it is meaningless to do so.

It is a counter-example inasmuch as it represents a relationship that one can
actually correlate, but it is theoretically vacuous.  If inflation and money
growth are cointegrated, then both are I(1) and the first differences of each
would appear in the ECM along with the cointegrating term (of course the first
differences would amount to second differences for these variables).  The same
would be the case for estimating a real money demand or supply relation.

I see no problem with your case involving real money, inflation, and money
growth.

Lonnie K. Stevans