Saving Summary Statistics for Groups

[See ANMBXSUM in the SAS/QC Sample Library]In this example, the BOXCHART statement is used to create a data set containing group summary statistics that can be read later by the ANOM procedure (as in the preceding example). The following statements read measurements from the data set LabelDeviations and create a summary data set named LabelSummary:

proc anom data=LabelDeviations;
   boxchart Deviation*Position / outsummary=LabelSummary
                                 nochart;
run;

The OUTSUMMARY= option names the output data set, and the NOCHART option suppresses the display of the chart, which would be identical to Figure 4.3.

Figure 4.6 contains a listing of LabelSummary.

Figure 4.6 The Summary Data Set LabelSummary
The Data Set LabelSummary

Position DeviationL Deviation1 DeviationX DeviationM Deviation3 DeviationH DeviationS DeviationN
1 -0.0647 -0.0362 -0.02234 -0.02620 -0.0016 0.0094 0.022807 10
2 -0.0332 -0.0201 0.01625 0.02045 0.0438 0.0564 0.033473 10
3 -0.0440 -0.0139 0.00604 0.00570 0.0285 0.0486 0.028849 10
4 0.0362 0.0530 0.06473 0.06030 0.0755 0.1073 0.021495 10
5 -0.0464 -0.0074 0.00813 0.00760 0.0302 0.0374 0.025928 10
6 -0.0384 -0.0285 -0.01283 -0.00950 0.0017 0.0071 0.015986 10

There are nine variables in the data set LabelSummary.

  • Position identifies the group.

  • DeviationL contains the group minimums.

  • Deviation1 contains the first quartile for each group.

  • DeviationX contains the group means.

  • DeviationM contains the group medians.

  • Deviation3 contains the third quartile for each group.

  • DeviationH contains the group maximums.

  • DeviationS contains the group standard deviations.

  • DeviationN contains the group sizes.

Note that the summary statistic variables are named by adding the suffix characters L, 1, X, M, 3, H, S, and N to the response Deviation specified in the BOXCHART statement. In other words, the variable naming convention for OUTSUMMARY= data sets is the same as that for SUMMARY= data sets.

For more information, see OUTSUMMARY= Data Set.