Boxplot Example Grouped by Machine

Difficulty Level

Beginner

Published on : 03/09/2024

This script illustrates the use of the BOXPLOT procedure to visualize quality control data. It first creates an internal dataset containing diameter measurements, sample number, and machine identifier. Then, it generates a graph where diameters are plotted by sample, with visual grouping by machine, allowing comparison of variations between different machines.

Data Analysis

Type : CREATION_INTERNE

Data is generated directly in the code via a DATA step and the DATALINES statement.

1 Code Block

DATA STEP Data

Explanation :
Creation of the SAS table 'Parts'. Use of a 'do i=1 to 4' loop to read four diameter measurements ('Diam') per raw data line for each combination of sample ('Sample') and machine ('Machine').

Copied!

1	DATA Parts;
2	LENGTH Machine $ 4;
3	INPUT Sample Machine $ @;
4	DO i= 1 to 4;
5	INPUT Diam @;
6	OUTPUT;
7	END;
8	drop i;
9	DATALINES;
10	1 A386 4.32 4.55 4.16 4.44
11	2 A386 4.49 4.30 4.52 4.61
12	3 A386 4.44 4.32 4.25 4.50
13	4 A386 4.55 4.15 4.42 4.49
14	5 A386 4.21 4.30 4.29 4.63
15	6 A386 4.56 4.61 4.29 4.56
16	7 A386 4.63 4.30 4.41 4.58
17	8 A386 4.38 4.65 4.43 4.44
18	9 A386 4.12 4.49 4.30 4.36
19	10 A455 4.45 4.56 4.38 4.51
20	11 A455 4.62 4.67 4.70 4.58
21	12 A455 4.33 4.23 4.34 4.58
22	13 A455 4.29 4.38 4.28 4.41
23	14 A455 4.15 4.35 4.28 4.23
24	15 A455 4.21 4.30 4.32 4.38
25	16 C334 4.16 4.28 4.31 4.59
26	17 C334 4.14 4.18 4.08 4.21
27	18 C334 4.51 4.20 4.28 4.19
28	19 C334 4.10 4.33 4.37 4.47
29	20 C334 3.99 4.09 4.47 4.25
30	21 C334 4.24 4.54 4.43 4.38
31	22 C334 4.23 4.48 4.31 4.57
32	23 C334 4.27 4.40 4.32 4.56
33	24 C334 4.70 4.65 4.49 4.38
34	;

2 Code Block

PROC BOXPLOT

Explanation :
Activation of ODS (Output Delivery System) graphics for modern rendering. Execution of the BOXPLOT procedure on the 'Parts' table. The 'plot' statement creates box plots of the 'Diam' variable for each 'Sample'. The '(Machine)' syntax specifies that the data should be grouped (stratified) by the 'Machine' variable.