StatTimeSerAnalysis.TripleExpForecast Method

Overload List

#	Signature	Description
1	procedure TripleExpForecast(const Y: TVec; const YHat: TVec; const Alpha: Double; const Beta: Double; const Gamma: Double; T: Integer; const Period: Integer);	Triple exponential forecast.
2	procedure TripleExpForecast(const Y: TVec; const YHat: TVec; var Alpha: Double; var Beta: Double; var Gamma: Double; const T: Integer; out MSE: Double; const Period: Integer);	First estimate Alpha, Beta and Gamma parameters by triple exponential smoothing and then use returned values to forecast up to T periods.

Triple exponential forecast.

#	Name	Description
1	Y	Time series data set.
2	YHat	Time series forecasts. Size of the YHat vector are adjusted automatically.
3	Alpha	Overal smoothing parameter used for forecast.
4	Beta	Trend smoothing parameter used for forecast.
5	Gamma	Seasonal smoothing parameter used for forecast.
6	T	Forecast values up to T period.
7	Period	Period length. An exception is raised if Y.Length mod Period is not 0.

Result: stored in self (calling object)

Remarks:

The h period ahead forecast is given by:

F[t+h] = (S[t]+h\cdot b[t])L[t-P] \quad .

where P is period length.

See Also: StatTimeSerAnalysis.TripleExpSmooth

First estimate Alpha, Beta and Gamma parameters by triple exponential smoothing and then use returned values to forecast up to T periods.

#	Name	Description
1	MSE	MSE, evaluated at minimum.
2	Y	Time series data set.
3	YHat	Time series forecasts. Size of the YHat vector are adjusted automatically.
4	Alpha	Overal smoothing parameter used for forecast.
5	Beta	Trend smoothing parameter used for forecast.
6	Gamma	Seasonal smoothing parameter used for forecast.
7	T	Forecast values up to T period.
8	Period	Period length. An exception is raised if Y.Length mod Period is not 0.

Result: stored in self (calling object)

Remarks:

Use this routine if you don't know the best estimates for Alpha, Beta and Gamma.