Hi All,
I have used ARIMA to model a periodical time series
constructed by arranging several "segments" each
representing a process. The processes are equal in
time so the result is a periodical times series. An
example of the segments would be several cash flows
for similar projects, but in reality not consecutively
executed in time. The models obtained are
statistically sound. The question is:
Is there a conceptual error in applying ARIMA to such
a data series?
regards to all
Tarek El-Sayed
__________________________________________________
Do You Yahoo!?
Great stuff seeking new owners in Yahoo! Auctions!
http://auctions.yahoo.com
|