Chapter Contents |
Previous |
Next |
MRCHART Statement |
See SHWMR1 in the SAS/QC Sample Library |
The previous example illustrates how you can create median and range charts using raw data (process measurements). However, in many applications, the data are provided as subgroup summary statistics. This example illustrates how you can use the MRCHART statement with data of this type.
The following data set (DETSUM) provides the data from the preceding
example in summarized form. There is exactly one observation for each
subgroup (note that the subgroups are
still indexed by LOT). The variable WEIGHTM contains the
subgroup medians, the variable WEIGHTR contains the
subgroup ranges, and the variable WEIGHTN contains
the subgroup sample sizes (these are all five).
data detsum; input lot weightm weightr; weightn = 5; datalines; 1 22.56 9.54 2 23.54 3.07 3 24.35 4.65 4 25.52 5.05 5 23.25 8.04 6 23.01 6.33 7 24.19 2.19 8 26.27 2.18 9 22.31 6.08 10 22.66 8.21 11 26.38 4.97 12 23.01 5.05 13 23.15 5.37 14 24.73 4.95 15 25.86 5.58 16 23.99 4.35 17 24.30 5.24 18 24.88 4.87 19 25.92 7.22 20 25.63 6.30 21 25.17 6.52 22 26.72 5.18 23 23.67 9.17 24 24.92 4.62 25 24.51 5.40 26 24.75 3.41 27 25.10 4.76 28 25.64 3.47 ;
A listing of DETSUM is shown in Figure 36.3.
You can read this data set by specifying it as a HISTORY= data set in the PROC SHEWHART statement, as follows:
title 'Median and Range Charts for Weights'; proc shewhart history=detsum lineprinter; mrchart weight*lot='*'; run;
The charts are shown in Figure 36.4. Since the LINEPRINTER option is included in the PROC SHEWHART statement, line printer output is provided. The asterisk (*) specified in single quotes after the subgroup-variable indicates the character used to plot points. This character must follow an equal sign.
Note that WEIGHT is not the name of a SAS variable in the data set DETSUM but is, instead, the common prefix for the names of the three SAS variables WEIGHTM, WEIGHTR, and WEIGHTN. The suffix characters M, R, and N indicate median, range, and sample size, respectively. This naming convention enables you to specify three subgroup summary variables in the HISTORY= data set with a single name (WEIGHT), referred to as the process. The name LOT specified after the asterisk is the name of the subgroup-variable.
|
In general, a HISTORY= input data set used with the MRCHART
statement must contain the following variables:
Furthermore, the names of the subgroup median, range, and sample size
variables must begin with the prefix process specified in
the MRCHART statement and end with the special suffix characters
M, R, and N, respectively.
If the names do not follow this
convention, you can use the RENAME option
to rename the variables for the duration of the SHEWHART
procedure step. Suppose that, instead of the variables WEIGHTM,
WEIGHTR, and WEIGHTN, the data set DETSUM contained summary
variables named MEDIANS, RANGES, and SIZES.
The following statements would temporarily rename
MEDIANS, RANGES, and SIZES to WEIGHTM, WEIGHTR, and WEIGHTN,
respectively:
proc shewhart history=detsum (rename=(medians = weightm ranges = weightr sizes = weightn )); mrchart weight*lot; run;
In summary, the interpretation of process depends on the
input data set:
For more information, see "HISTORY= Data Set".
Chapter Contents |
Previous |
Next |
Top |
Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.