Chapter Contents
Chapter Contents
Previous
Previous
Next
Next
XRCHART Statement

Methods for Estimating the Standard Deviation

When control limits are determined from the input data, two methods (referred to as default and MVLUE) are available for estimating \sigma.

Default Method

The default estimate for \sigma is
\hat{\sigma} = \frac{R_{1}/d_{2}(n_{1})+  ...  + R_{N}/d_{2}(n_{N})}
 N
where N is the number of subgroups for which n_i \geq 2, and Ri is the sample range of the observations xi1, . . . ,x_{in_{i}} in the i th subgroup.
R_{i} = \max_{1 \leq j \leq n_{i}}(x_{ij}) - \min_{1 \leq j \leq n_{i}}(x_{ij})
A subgroup range Ri is included in the calculation only if n_i \geq 2.The unbiasing factor d2(ni) is defined so that, if the observations are normally distributed, the expected value of Ri is d_{2}(n_i)\sigma.Thus, \hat{\sigma} is the unweighted average of N unbiased estimates of \sigma.This method is described in the ASTM Manual on Presentation of Data and Control Chart Analysis (1976).

MVLUE Method

If you specify SMETHOD=MVLUE, a minimum variance linear unbiased estimate (MVLUE) is computed for \sigma. Refer to Burr (1969, 1976) and Nelson (1989, 1994). The MVLUE is a weighted average of N unbiased estimates of \sigma of the form Ri/d2(ni), and it is computed as
\hat{\sigma} = \frac{f_{1}R_{1}/d_{2}(n_{1})+  ...  + f_{N}R_{N}/d_{2}(n_{N})}
 {f_1 +  ...  + f_N}
where
fi = [([d2(ni)]2)/([d3(ni)]2)]

A subgroup range Ri is included in the calculation only if n_i \geq 2, and N is the number of subgroups for which n_i \geq 2. The unbiasing factor d3(ni) is defined so that, if the observations are normally distributed, the expected value of \sigma_{R_{i}} is d_{3}(n_i)\sigma.The MVLUE assigns greater weight to estimates of \sigma from subgroups with larger sample sizes, and it is intended for situations where the subgroup sample sizes vary. If the subgroup sample sizes are constant, the MVLUE reduces to the default estimate.

Chapter Contents
Chapter Contents
Previous
Previous
Next
Next
Top
Top

Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.