A
analyst41
I'd appreciate help with the following problem:
There is a time series x(1),x(2),....X(30).
On day t, you have observed X(1),X(2),...X(t).
You make a forecast for the value of X for days t+1,t+2,... 30.
This forecast would involve past forecasts and past observations
(typically, single, double or triple exponential smoothing).
When day t+1 rolls around, a new forecast is made for days t+2,...30,
This forecast is the same formula as the previous day's, but every
observation is shifted one day into the future.
I'd like to do this in two columns, Every day, the X column should
contain the observed actuals for each day up to and including that
day. The forecast column for each day should contain the last
forecast made for that day (ie today's forecast for future days and
the previous day's forecast for today and past days).
As the forecasting method, we can use a 7 day moving average for
illustrative purposes.
There is a time series x(1),x(2),....X(30).
On day t, you have observed X(1),X(2),...X(t).
You make a forecast for the value of X for days t+1,t+2,... 30.
This forecast would involve past forecasts and past observations
(typically, single, double or triple exponential smoothing).
When day t+1 rolls around, a new forecast is made for days t+2,...30,
This forecast is the same formula as the previous day's, but every
observation is shifted one day into the future.
I'd like to do this in two columns, Every day, the X column should
contain the observed actuals for each day up to and including that
day. The forecast column for each day should contain the last
forecast made for that day (ie today's forecast for future days and
the previous day's forecast for today and past days).
As the forecasting method, we can use a 7 day moving average for
illustrative purposes.