BOXCHART Statement: SHEWHART Procedure

Syntax: BOXCHART Statement

The basic syntax for the BOXCHART statement is as follows:

BOXCHART process subgroup-variable ;

The general form of this syntax is as follows:

BOXCHART processes subgroup-variable <(block-variables)><=symbol-variable | ='character'> / <options> ;

You can use any number of BOXCHART statements in the SHEWHART procedure. The components of the BOXCHART statement are described as follows.

process processes

identify one or more processes to be analyzed. The specification of process depends on the input data set specified in the PROC SHEWHART statement.

If raw data are read from a DATA= data set, process must be the name of the variable containing the raw measurements. For an example, see Creating Box Charts from Raw Data.
If summary data are read from a HISTORY= data set, process must be the common prefix of the summary variables in the HISTORY= data set. For an example, see Creating Box Charts from Subgroup Summary Data.
If summary data and control limits are read from a TABLE= data set, process must be the value of the variable _VAR_ in the TABLE= data set. For an example, see Saving Control Limits.

A process is required. If you specify more than one process, enclose the list in parentheses. For example, the following statements request distinct box charts for Weight, Length, and Width:

proc shewhart data=summary;
   boxchart (Weight Length Width)*Day;
run;

subgroup-variable

is the variable that identifies subgroups in the data. The subgroup-variable is required. In the preceding BOXCHART statement, Day is the subgroup variable. For details, see Subgroup Variables.

block-variables

are optional variables that group the data into blocks of consecutive subgroups. These blocks are labeled in a legend, and each block-variable provides one level of labels in the legend. See Displaying Stratification in Blocks of Observations for an example.

symbol-variable

is an optional variable whose levels (unique values) determine the symbol marker or character used to plot the means.

If you produce a line printer chart, an 'A' is displayed for the points corresponding to the first level of the symbol-variable, a 'B' is displayed for the points corresponding to the second level, and so on.
If you produce traditional graphics, distinct symbol markers are displayed for points corresponding to the various levels of the symbol-variable. You can specify the symbol markers with SYMBOLn statements. See Displaying Stratification in Levels of a Classification Variable for an example.

character

specifies a plotting character for line printer charts. For example, the following statements create a box chart using an asterisk (*) to plot the means:

proc shewhart data=values lineprinter;
   boxchart weight*day='*';
run;

options

enhance the appearance of the box chart, request additional analyses, save results in data sets, and so on. The Summary of Options section, which follows, lists all options by function. Dictionary of Options: SHEWHART Procedure describes each option in detail.