Google
 

Trailing-Edge - PDP-10 Archives - decus_20tap2_198111 - decus/20-0026/exsmo.doc
There are 2 other files named exsmo.doc in the archive. Click here to see a list.
SUBROUTINE EXSMO

PURPOSE
   TO FIND THE TRIPLE EXPONENTIAL SMOOTHED SERIES S OF THE
   GIVEN SERIES X.

USAGE
   CALL EXSMO (X,NX,AL,A,B,C,S)

DESCRIPTION OF PARAMETERS
   X	 - INPUT VECTOR OF LENGTH NX CONTAINING TIME SERIES
	   DATA WHICH IS TO BE EXPONENTIALLY SMOOTHED.
   NX	 - THE NUMBER OF ELEMENTS IN X.
   AL	 - SMOOTHING CONSTANT, ALPHA.  AL MUST BE GREATER THAN
	   ZERO AND LESS THAN ONE.
   A,B,C - COEFFICIENTS OF THE PREDICTION EQUATION WHERE S IS
	   PREDICTED T PERIODS HENCE BY
			 A + B*T + C*T*T/2.
	   AS INPUT-- IF A=B=C=0, PROGRAM WILL PROVIDE INITIAL
	   VALUES.  IF AT LEAST ONE OF A,B,C IS NOT ZERO,
	   PROGRAM WILL TAKE GIVEN VALUES AS INITIAL VALUES.
	   AS OUTPUT-- A,B,C CONTAIN LATEST, UPDATED COEFFI-
	   CIENTS OF PREDICTION.
   S	 - OUTPUT VECTOR OF LENGTH NX CONTAINING TRIPLE
	   EXPONENTIALLY SMOOTHED TIME SERIES.

REMARKS
   NONE

SUBROUTINES AND FUNCTION SUBPROGRAMS REQUIRED
   NONE

METHOD
   REFER TO R. G. BROWN, 'SMOOTHING, FORECASTING AND PREDICTION
   OF DISCRETE TIME SERIES', PRENTICE-HALL, N.J., 1963,
   PP. 140 TO 144.