On 31 Mar 2000, Victor Aina wrote:
> I've got 2 non-overlapping periods. Data is
> available for period one (the first period).
> The intention is to predict observations that
> will be coming in period 2.
This is not very informative. "Period" suggests you have data
values for several points in time during "period 1"; is "several"
a number like 3, or 30, or 300, ...? And do you have a single
observation at each time point, or multiple observations? Etc.
> Now, suppose an extra information is available for
> period 2. In particular, suppose it is known that
> the values of observations in the 1st half of
> period two will increase, and thereafter level off.
Is this different from behavior in the first period?
If so, what connection do you see/theorize/hypothesize/
conjecture between the two periods?
If not, why not model the second period on the first?
> My question is what options are available for
> capturing (in a regression model) such problem?
> And what are the caveats and/or pitfalls?
It sounded to me as though you do not have data for the second
period, but only for the first. If this is the case, I fail to
see how one could hope to "capture" one's prediction for period 2
in a model. One could of course prepare a model, based on period
1, and arranged to report the differences between observed and
predicted values when period 2 observations become available.
If I have misunderstood the situation, then setting up
some sort of "predictive" model and fitting it to period 2 data
is of course possible. One might then think of the period 2 data
as supplying a validation sample for the model developed in period 1;
although, given your remarks about what is known about period 2, and
assuming that it's qualitatively different from period 1, I'd be VERY
skeptical...
-- DFB.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
