 
      SUBROUTINE SCALE(MM, M, N, A, KL, KK)
C
C<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
C
C   PURPOSE
C   -------
C
C      DISCRETIZES THE DATA INTO CLASSES
C
C   DESCRIPTION
C   -----------
C
C   1.  THE MINIMUM AND MAXIMUM VALUES ARE FOUND AND EACH VALUE IS THEN
C       PLACED INTO ONE OF KL INTERVALS OF EQUAL LENGTH BETWEEN THE
C       MINIMUM AND MAXIMUM VALUES.
C
C   2.  THE USER HAS THE OPTION TO EITHER SCALE UNIFORMLY OVER ALL DATA
C       VALUES, OR TO UNIFORMLY SCALE EACH VARIABLE.
C
C   INPUT PARAMETERS
C   ----------------
C
C   MM    INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         THE FIRST DIMENSION OF THE MATRIX A.  MUST BE AT LEAST M.
C
C   M     INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         THE NUMBER OF CASES.
C
C   N     INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         THE NUMBER OF VARIABLES.
C
C   A     REAL MATRIX WHOSE FIRST DIMENSION MUST BE MM AND WHOSE SECOND
C            DIMENSION MUST BE AT LEAST N (CHANGED ON OUTPUT).
C         THE MATRIX OF DATA VALUES WHICH WILL BE SCALED ON OUTPUT.
C
C   KL    INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         MAXIMUM SCALED VALUE.
C
C   KK    INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         SCALING OPTION.
C
C         IF KK = 1   DATA ARE SCALED UNIFORMLY OVER ALL VALUES
C         IF KK = 2   DATA ARE SCALED UNIFORMLY OVER EACH VARIABLE
C
C   OUTPUT PARAMETER
C   ----------------
C
C   A     REAL MATRIX WHOSE FIRST DIMENSION MUST BE MM AND WHOSE SECOND
C            DIMENSION MUST BE AT LEAST N.
C         THE MATRIX OF SCALED DATA VALUES.
C
C   REFERENCE
C   ---------
C
C     HARTIGAN, J. A. (1975).  CLUSTERING ALGORITHMS, JOHN WILEY &
C        SONS, INC., NEW YORK.  PAGES 148, 151.
C
C<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
C
 
 
