SUBROUTINE HIST(NPTS, X, XMIN, XMAX, NI, P, TITLE, OUNIT)
C
C<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
C
C   PURPOSE
C   -------
C
C      PRINTS A UNIVARIATE HISTOGRAM
C
C   DESCRIPTION
C   -----------
C
C   1.  EACH VALUE IS INITIALLY MAPPED INTO ONE OF 100 BINS AND THEN
C       THE BINS ARE GATHERED TOGETHER INTO NI BINS.  THE LARGEST
C       NUMBER OF VALUES IN A BIN IS FOUND, WHICH WILL DETERMINE THE
C       VERTICAL HEIGHT OF THE PRINTED HISTOGRAM.  THE HISTOGRAM IS
C       THEN PRINTED WITH THE CHARACTER 'O' DENOTING EACH OCCURRENCE.
C
C   2.  THE PARAMETER NI IS THE NUMBER OF HISTOGRAM BINS DESIRED.  THE
C       NUMBER OF COLUMNS IN THE PRINTED HISTOGRAM WILL BE 100
C       INDEPENDENT OF THE CHOICE OF NI.  IF 100 HISTOGRAM BINS ARE
C       SPECIFIED, EACH COLUMN WILL CORRESPOND TO ONE BIN.  IF NI = 25,
C       THE FIRST FOUR (100/NI) COLUMNS OF THE PRINTED HISTOGRAM WILL
C       CORRESPOND TO THE FIRST BIN.  THE VALUE FOR THE BIN WILL BE THE
C       VALUE FOUND IN EACH OF THE FIRST FOUR COLUMNS.  THE PRINTED
C       HISTOGRAM IS OUTPUT ON FORTRAN UNIT OUNIT.
C
C   INPUT PARAMETERS
C   ----------------
C
C   NPTS  INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         THE NUMBER OF DATA POINTS.
C
C   X     REAL VECTOR DIMENSIONED AT LEAST NPTS (UNCHANGED ON OUTPUT).
C         THE DATA VALUES.
C
C   NI    INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         THE NUMBER OF HISTOGRAM BINS.
C
C         NI SHOULD NOT BE GREATER THAN 100 AND SHOULD BE A FACTOR OF
C         100.  IF NI = 0 ON INPUT, THE DEFAULT VALUE OF NI = 100 WILL
C         BE USED.
C
C   P     REAL SCALAR (UNCHANGED ON OUTPUT).
C         THE DIVISOR FOR THE VERTICAL SCALE. 1/P DENOTES THE NUMBER OF
C            SYMBOLS FOR EACH OCCURRENCE IN A BIN.
C
C         IF P = 0. ON INPUT, THE DEFAULT VALUE OF P = 1. WILL BE USED.
C
C   TITLE 4-CHARACTER VARIABLE (UNCHANGED ON OUTPUT).
C         TITLE OF THE DATA SET.
C
C   OUNIT INTEGER SCALAR (UNCHANGED ON OUTPUT).
C         UNIT NUMBER FOR OUTPUT.
C
C   REFERENCES
C   ----------
C
C     HARTIGAN, J. A. (1975).  CLUSTERING ALGORITHMS, JOHN WILEY &
C        SONS, INC., NEW YORK.  PAGE 47.
C
C     HARTIGAN, J. A. (1975) PRINTER GRAPHICS FOR CLUSTERING. JOURNAL OF
C        STATISTICAL COMPUTATION AND SIMULATION. VOLUME 4,PAGES 187-213.
C
C<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
C