Chapter 7: The CHART Procedure
Overview: CHART Procedure
What Does the CHART Procedure Do?
The CHART procedure produces vertical and horizontal bar charts, block charts, pie charts, and star charts. These types of charts graphically display values of a variable or a statistic associated with those values. The charted variable can be numeric or character.
PROC CHART is a useful tool that lets you visualize data quickly, but if you need to produce presentation-quality graphics that include color and various fonts, then use SAS/GRAPH software. The GCHART procedure in SAS/GRAPH software produces the same types of charts as PROC CHART does. In addition, PROC GCHART can produce donut charts.
What Types of Charts Can PROC CHART Create?
Bar Charts
Horizontal and vertical bar charts display the magnitude of data with bars, each of which represents a category of data. The length or height of the bars represents the value of the chart statistic for each category.
Output 7.1 shows a vertical bar chart that displays the number of responses for the five categories from the survey data. The following statements produce the output:
 |
The SAS System 1 Count Sum 200 + ***** ***** ***** ***** ***** 150 + ***** ***** ***** ***** ***** ***** ***** ***** 100 + ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** 50 + ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** -------------------------------------------------------------------- Always Usually Sometimes Rarely Never Response
| |
options nodate pageno=1 linesize=80 pagesize=30; proc chart data=survey; vbar response / sumvar=count midpoints='Always' 'Usually' 'Sometimes' 'Rarely' 'Never'; run;
Output 7.2 shows the same data presented in a horizontal bar chart. The two types of bar charts have essentially the same characteristics, except that horizontal bar charts by default display a table of statistic values to the right of the bars. The following statements produce the output:
| |
The SAS System 1 Response Count Sum Always ********************* 106.0000 Usually **************************************** 202.0000 Sometimes ************************ 119.0000 Rarely ******************* 97.0000 Never ********* 44.0000 ----+---+---+---+---+---+---+---+---+---+ 20 40 60 80 100 120 140 160 180 200 Count Sum
| |
options nodate pageno=1 linesize=80 pagesize=60; proc chart data=survey; hbar response / sumvar=count midpoints='Always' 'Usually' 'Sometimes' 'Rarely' 'Never'; run;
Block Charts
Block charts display the relative magnitude of data by using blocks of varying height, each set in a square that represents a category of data. Output 7.3 shows the number of each survey response in the form of a block chart.
| |
The SAS System 1 Sum of Count by Response ___ /_ / ** ** ** ___ ___ ** /_ / ___ /_ / ** ** /_ / -** --------** --------** --------** --------------------- / ** / ** / ** / ** / ___ / / ** / ** / ** / ** / /_ / / / ** / ** / ** / ** / ** / / **/ / **/ / **/ / **/ / **/ / / / / / / / / 106 / 202 / 119 / 97 / 44 / /-------------/-------------/-------------/-------------/-------------/ Always Usually Sometimes Rarely Never Response
| |
options nodate pageno=1 linesize=80 pagesize=30; proc chart data=survey; block response / sumvar=count midpoints='Always' 'Usually' 'Sometimes' 'Rarely' 'Never'; run;
Pie Charts
Pie charts represent the relative contribution of parts to the whole by displaying data as wedge -shaped slices of a circle. Each slice represents a category of the data. Output 7.4 shows the survey results divided by response into five pie slices. The following statements produce the output:
| |
The SAS System 1 Sum of Count by Response Never *********** Rarely **** . **** ** . . ** ** . 44 . ** * .7.75%. * Always ** 97 . .. ** ** 17.08% . . ** * .. . . 106 * * .. . . 18.66% * * .. . .. * * . . * * + . . .. . .. . .* * 119 * * 20.95% .. * Sometimes * . * * . * ** . 202 ** * .. 35.56% * * . * ** . ** ** ** **** **** *********** Usually
| |
options nodate pageno=1 linesize=80 pagesize=35; proc chart data=survey; pie response / sumvar=count; run;
Star Charts
With PROC CHART, you can produce star charts that show group frequencies, totals, or mean values. A star chart is similar to a vertical bar chart, but the bars on a star chart radiate from a center point, like spokes in a wheel. Star charts are commonly used for cyclical data, such as measures taken every month or day or hour , or for data like these in which the categories have an inherent order ( always meaning more frequent than usually which means more frequent than sometimes ). Output 7.5 shows the survey data displayed in a star chart. The following statements produce the output:
| |
The SAS System 1 Center = 0 Sum of Count by Response Outside = 202 Never ************* 44 ***** ***** *** *** *** *** ** ** * * Rarely ** ** 97 * * ** ** * * * * ** ** * *...... * ** . .. ......*. ** * .. .. .. ... * * . .. . .... * * . .. .. ... * * . .+..............* * Always * . .. .. . * 106 * . ... . . * * . . . . * ** .. ... . .. ** * . .. . . * ** *. .. . ** * .. . .. * * .. . . * * .. . .. * * ... .. . * Sometimes ** .. . . ** 119 * ... . .. * ** . . . ** *** ... . . *** *** .... *** ***** *.*** ************* Usually 202
| |
options nodate pageno=1 linesize=80 pagesize=60; proc chart data=survey; star response / sumvar=count; run;
EAN: 2147483647
Pages: 260