Re: Covariation of curves

"W. Bauer" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>...
> [EMAIL PROTECTED] (David Reilly) wrote in
> > As I understand your statement "I observe a time series for each of N
> > step functions" ...this means to me that you observe a sequence in
> > time of real
> > values for EACH of n steps ....
> 
> Yes, I observe at each point of time the whole curve. But the points where 
> the jumps are change over time. Does this pose a problem for the "pooled
> cross-sectional time series" methodology?
> 
> Thanks for the hint, W. Bauer

No ... Because the assumption is that there are N GROUPS or N SEPARATE
AND DISTINCT REGIMES and each regime has t observed contiguous values
( not necessarily equal for all groups ) ..

regards

Dave Reilly
Automatic Forecasting Systems
http://www.autobox.com
215-675-0652