Chapter Contents |
Previous |
Next |
PCHART Statement |
See SHWPEX1 in the SAS/QC Sample Library |
This example
shows how you can apply tests for special causes
to make p charts more sensitive to special causes of variation.
The following statements create a SAS data set named
CIRCUIT3, which contains the number of failing circuits
for 20 batches from the circuit manufacturing process
introduced in "Creating p Charts from Count Data":
data circuit3; input batch fail @@; datalines; 1 12 2 21 3 16 4 9 5 3 6 4 7 6 8 9 9 11 10 13 11 12 12 7 13 2 14 14 15 9 16 8 17 14 18 10 19 11 20 9 ;
The following statements create the p chart,
apply several tests to the chart, and tabulate the results:
title1'p Chart for the Proportion of Failing Circuits'; title2 'Tests = 1 to 4'; symbol v=dot c=salmon; proc shewhart data=circuit3; pchart fail*batch / subgroupn = 500 tests = 1 to 4 ltests = 20 zonelabels tabletest tablelegend cframe = lib cinfill = bwh coutfill = yellow czones = lib ctests = cxfefefe cconnect = salmon; run;
The chart is shown in Output 38.1.1, and the printed output is shown in Output 38.1.2. The TESTS= option requests Tests 1, 2, 3, and 4, which are described in Chapter 48, "Tests for Special Causes." The TABLETESTS option requests a table of proportions of nonconforming items and control limits, with a column indicating which subgroups tested positive for special causes. The TABLELEGEND option adds a legend describing the tests that are positive.
The ZONELABELS option displays zone lines and zone labels on the chart. The zones are used to define the tests. The LTESTS= option specifies the line type used to connect the points in a pattern for a test that is signaled. Output 38.1.1 and Output 38.1.2 indicate that Test 1 is positive at batch 2 and Test 3 is positive at batch 10.
Output 38.1.1: Tests for Special Causes Displayed on p Chart
Chapter Contents |
Previous |
Next |
Top |
Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.