Saving Proportions of Nonconforming Items

[See SHWPCHR in the SAS/QC Sample Library]In this example, the PCHART statement is used to create a data set that can later be read by the SHEWHART procedure (as in the preceding example). The following statements read the number of nonconforming items from the data set Circuits (see Creating p Charts from Count Data) and create a summary data set named Cirhist:

proc shewhart data=Circuits;
   pchart Fail*Batch / subgroupn  = 500
                       outhistory = Cirhist
                       nochart ;
run;

The OUTHISTORY= option names the output data set, and the NOCHART option suppresses the display of the chart, which would be identical to the chart in Figure 13.21.4. Figure 13.21.8 contains a partial listing of Cirhist.

There are three variables in the data set Cirhist.

• Batch contains the subgroup index.

• FailP contains the subgroup proportion of nonconforming items.

• FailN contains the subgroup sample size.

Note that the variables containing the subgroup proportions of nonconforming items and subgroup sample sizes are named by adding the suffix characters P and N to the process Fail specified in the PCHART statement. In other words, the variable naming convention for OUTHISTORY= data sets is the same as that for HISTORY= data sets. For more information, see OUTHISTORY= Data Set.