Whilst simulating, at t=t1 I want to know the FORECAST at t=T (T>t1) of two time functions (say f(T) and F(T)) where F(T) is the integral of f(t) over [t1,T] (iow F(T) = int from t=t1 to t=T f(t) dt). f(T) can be obtained by the FORECAST function, but how about F(T)...? Does anyone know how to do this?
[Edited on 9-18-2009 by burley]
FORECAST
-
- Senior Member
- Posts: 1107
- Joined: Wed Mar 12, 2003 2:46 pm
if you use
forecasted val = FORECAST(val,averaging time,horizon)
then
cumulated forecast = INTEG(forecasted val-old forecasted val,forecasted val*horizon)
where
old forecasted val = DELAY FIXED(forecasted val,horizon)
will give you what you want. You may need to use
adjusted cumulated forecast = cumulated forecast + TIME STEP*(forecasted val - old forecasted val)
to get the current period value in place.
forecasted val = FORECAST(val,averaging time,horizon)
then
cumulated forecast = INTEG(forecasted val-old forecasted val,forecasted val*horizon)
where
old forecasted val = DELAY FIXED(forecasted val,horizon)
will give you what you want. You may need to use
adjusted cumulated forecast = cumulated forecast + TIME STEP*(forecasted val - old forecasted val)
to get the current period value in place.