It's not hard to see why Wheeler says that CUSUM is a chart that only its
mother would love ...
Rather than jumping in blindly, it would be insightful to ask why your
client wants to use these charts rather than Shewhart Charts.
There is no need to "normalise the variance". Wheeler discusses this in
great detail in the wonderful little book he has written on this topic
"Normaility and the Process Behaviour Chart", SPC Press.
Dr Tony Burns
<partho61@[EMAIL PROTECTED]
> wrote in message
news:1183106339.370155.40170@[EMAIL PROTECTED]
> Hello all!
>
> Greetings. I am involved in developing SQC tools. Recently a client
> asked whether it is possible to design a EWMA or CUSUM type control
> chart for the process <variance> (or <standard deviation>). My first
> reaction was that it probably would not be a good idea, since the
> variance has a probability distribution that is not Normal, or
> additive. It seems, though, that CUSUM/EWMA Control Charts for the
> variance have been developed, e.g., A New S2-EWMA Control Chart for
> Monitoring the Process Variance, Philippe Castagliola, EWMA for
> monitoring a process standard deviation, Crowder & Hamilton. I have
> just downloaded the first paper (http://www3.interscience.wiley.com/
> user/accessdenied?ID=110494448&Act=2138&Code=4719&Page=/cgi-bin/
> fulltext/110494448/PDFSTART), which is apparently an improvement over
> the earlier Crowder & Hamilton paper (Crowder SV, Hamilton MD. An EWMA
> for monitoring a process standard deviation. Journal of Quality
> Technology
> 1992; 24(1):12-21)- I have not seen this paper. the basic idea of
> these authors seems to be to use a logarithmic transformation to
> "normalise" the variance.
>
> So now (before I try to program and make this tool available to my
> client!) my question is: does anyone here have experience of using
> these charts? I don't think they have been incor****ated in any SPC
> software that I have come across, which adds to my reservation!
>
> Thanks and Regards
> ESG
>
|
