| Computing Statistics for Numeric Variables |
| Group
Processing |
| CLASS Group Processing
You will often want statistics for grouped observations, instead of for observations as a whole. For example, census numbers are more useful when grouped by region than when viewed as a national total. To produce separate analyses of grouped observations, add a CLASS statement to the MEANS procedure. |
General form, CLASS statement:
where variable(s) specifies category variables for group processing. |
| PROC MEANS will not generate statistics for CLASS variables because their
values are only used to categorize data. Thus, CLASS variables can be either
character or numeric.
The output of the program shown below is categorized by values of the variables
proc means data=clinic.heart maxdec=1;
var arterial heart cardiac urinary;
class survive sex;
run;
|
| Survive | Sex | Variable | N | Mean | Minimum | Maximum | ||
| DIED | 1 | 4 | Arterial Heart Cardiac Urinary |
4 4 4 4 |
92.5 111.0 176.8 98.0 |
10.5 53.4 75.2 186.1 |
83.0 54.0 95.0 0.0 |
103.0 183.0 260.0 377.0 |
| 2 | 6 | Arterial Heart Cardiac Urinary |
6 6 6 6 |
94.2 103.7 318.3 100.3 |
27.3 16.7 102.6 155.7 |
72.0 81.0 156.0 0.0 |
145.0 130.0 424.0 405.0 |
|
| SURV | 1 | 5 | Arterial Heart Cardiac Urinary |
5 5 5 5 |
77.2 109.0 298.0 100.8 |
12.2 32.0 139.8 60.2 |
61.0 77.0 66.0 44.0 |
88.0 149.0 410.0 200.0 |
| 2 | 5 | Arterial Heart Cardiac Urinary |
5 5 5 5 |
78.8 100.0 330.2 111.2 |
6.8 13.4 87.0 152.4 |
72.0 84.0 256.0 12.0 |
87.0 111.0 471.0 377.0 |
     |
|
|
|
Copyright © 2002 SAS Institute Inc.,
Cary, NC, USA. All rights reserved.