Re: Letter form Bob Solow

["Lonnie K. Stevans" <acslks@xxxxxxxxxxxxxxxxx>]

Sorry, ignore my previous posting:

Sounds like a Type II error to me.  It is certainly plausible to observe the presence of a unit
root when the alternative hypothesis of no unit root is true, e.g., if the probability of a Type
II error was .10, then by performing 100 Monte Carlo simulations of white noise, you will
wind up making the "mistake" of accepting the null hypothesis of a unit root ten times.
Yaglom just happened to observe one of those outcomes and it would seem to me that
he should have repeated the experiment a number of times.

Lonnie K. Stevans
acslks@xxxxxxxxxxx

>>> pdavidso <pdavidso@xxxxxxx> 11/12/02 10:41AM >>>
>===== Original Message From "Lonnie K. Stevans" <acslks@xxxxxxxxxxxxxxxxx>
=====
>I obviously cannot speak for Granger, but the procedure is to test for
presence/absence of a
>unit root before testing for cointegration.  It would seem to me that the
process of just
>arbitrarily taking nth-differences without testing for multiple unit roots is
a
>"meaningless exercise."
>


It was not meaningless.  Obviously , as i said "Yaglom took a randon number
generator and
>generated two column of random numbers.  Not surprisingly he foud a unit root
>for these columns."

So Yaglom originally found a unit root -- and then tried differencing!!!


Paul

Paul Davidson
Editor, Journal of Post Keynesian Economics
University of Tennessee
SMC 523
Knoxville, Tennessee 37996-0550
phone # (865)974-4221; fax #(561)737-8262;
email pdavidson@xxxxxxx
http://econ.bus.utk.edu/davidsonextra/Davidson.html