Advances and Applications in Statistics
Volume 2, Issue 2, Pages 189 - 198
(August 2002)
|
|
CAPABILITY EVALUATION FOR PROCESSES OF THE LARGER-THE- BETTER TYPE FOR NON-NORMAL POPULATIONS
S. J. Liao (Taiwan), K. S. Chen (Taiwan) and R. K. Li (Taiwan)
|
Abstract: Process
Capability Indices (PCIs) have proliferated in both
use and variety during the last decade. Many
statisticians and quality control engineers studied
the indices of processes so that the precision of
assessing the quality and efficiency of a process
can be enhanced. However, these studies depend
heavily on the assumption of normal variability.
Process data do not always follow a normal
distribution. A one-sided specification limit is an
immediate clue that the data might be non-normal. If
the underlying distributions are non-normal, then
the capability calculations are highly unreliable
since the conventional estimator S2 of
s2is
sensitive to departures from normality, and
estimators of those indices are calculated using S2.Therefore,
those basic indices are inappropriate for processes
with non-normal distribution. Thus, in this paper,
we propose index CNpl
to evaluate the case, where the
underlying distributions may not be normal, provide
comparisons between Cpl
and CNpl
indices and present a case study to illustrate how
the index CNpl
may be applied to actual data collected from the
factories. |
Keywords and phrases: process capability indices, the larger-the-better type, non-normal distribution. |
|
Number of Downloads: 5 | Number of Views: 949 |
|