SAS系统绘图模块操作手册.doc

The GCHART Procedure Overview The GCHART procedure produces six types of charts: block charts, horizontal and vertical bar charts, pie and donut charts, and star charts. These charts graphically represent the value of a statistic calculated for one or more variables in an input SAS data set. The charted variables can be either numeric or character. The procedure calculates these statistics: frequency or cumulative frequency counts percentages or cumulative percentages sums means. Use the GCHART procedure to display and compare exact and relative magnitudes examine the contribution of parts to the whole analyze where data are out of balance. About Block Charts Block charts display the relative magnitude of data with blocks of varying height, each set in a square that represents a category of data (midpoint). Because block charts do not use axes, they are most useful when the relative magnitude of the blocks is more significant than the exact magnitude of any particular block. Block Chart (GR13N01) shows a simple block chart of total sales for three manufacturing sites. Each site is a midpoint and occupies one square. The name of the site (the midpoint value) is printed below the square. Midpoint values are, by default, arranged in ascending order from left to right. The label below the midpoint grid names the chart variable. Sales for the site (the chart statistic) are represented by the height of the block; sales amount (the formatted statistic value) is printed below the block. The heading above the blocks describes the type of statistic, in this case SUM. Block Chart (GR13N01) The program for this chart is in Specifying the Sum Statistic in a Block Chart. For more information on producing block charts, see BLOCK Statement. About Bar Charts Horizontal and vertical bar charts display the magnitude of data with bars, each of which represents a category of data (midpoint). The length (or height) of the bars represents the value of the chart statist