Coefficient of Variation …
Six Sigma – iSixSigma › Forums › Old Forums › General › Coefficient of Variation …
 This topic has 10 replies, 10 voices, and was last updated 15 years, 10 months ago by Brian P.

AuthorPosts

November 28, 2001 at 6:27 pm #28286
MAStoughParticipant@MAStough Include @MAStough in your post and this person will
be notified via email.I’m interested in opinions around the use of the Coefficient of Variation (i.e., standard deviation / mean).
Pros (to using it) and examples
Cons (to using it) and why
Any other thoughts?
Many thanks!0November 29, 2001 at 9:25 am #70230Hi,
Coeffecient of varation helps you to find out whether you want to consider one sigam or 3 sigma to develop control charts. THis is only recommendation. When your sigma is very high if you take 3 sigma values almost every point will fall in within control because of large distance between control limits and centre value. To avoid this we check the Coeffecient of variation and decide upon the control limits.
Hope this gives some idea
bye0November 29, 2001 at 5:51 pm #70259
Dave StrouseParticipant@DaveStrouse Include @DaveStrouse in your post and this person will
be notified via email.Sridhar –
I hate to flame anyone and perhaps I misunderstood your post, so I will say this as nicely as I can.
If you are using one sigma control limits on any control chart and / or you truely believe that the proportion of points falling within 3 sigma limits is related to the absolute magnitude of the sigma, please seek competant instruction in SPC. Both of theose statements are absolutely contrary to accepted theory, practice, and fact.
CV is just a convienent way to compare relative variation of two measurements with dissimilar means. It is very common measure in analytic laboratories where the control fluids may be at different means, bu5t the relative precision of the measurements at those levels must be similar.
0December 1, 2001 at 5:52 am #70315MAStough,In general practice the CV is used when you know or observe that the variation of a process or measurement system is dependent upon the mean. In such cases as the mean increases the standard deviation will also increase linearly with the mean. To decouple this relationship you compute the incremental variation by computing the CV. I have not seen examples where the CV was used directly to compute control limits, but perhaps there are a few examples in the journals that I’ve missed.Take care,Ken
0December 3, 2001 at 6:17 pm #70363COV is a very powerful tool to take a process and to search for the greatest sources of variation within it. To get the maximum effectiveness you have to have an idea of what youre looking for. Is variability a factor of time, location, or as things come off serially. I typically recommend that BBs perform this analysis prior to launching into a DOE. Its also a good check to see if there is understanding of the process and that define, measure, and analyze are progressing . The information that you gain from this analysis can make the subsequent DOE much more powerful and hone in on the true critical Xs.
Regards,
Erik0December 3, 2001 at 6:17 pm #70364COV is a very powerful tool to take a process and to search for the greatest sources of variation within it. To get the maximum effectiveness you have to have an idea of what youre looking for. Is variability a factor of time, location, or as things come off serially. I typically recommend that BBs perform this analysis prior to launching into a DOE. Its also a good check to see if there is understanding of the process and that define, measure, and analyze are progressing . The information that you gain from this analysis can make the subsequent DOE much more powerful and hone in on the true critical Xs.
Regards,
Erik0October 3, 2002 at 8:40 pm #79431To All:
Can anyone briefly explain the difference between a nested c.o.v and crossed c.o.v?
Thanks0March 27, 2003 at 4:55 am #84200
deepeshParticipant@deepesh Include @deepesh in your post and this person will
be notified via email.hi,
COV is a measure of relative dispersion of data.it tells us how mean and standard deviation vary on both sides of the distribution table.The COV calculated tells us about the sensitivity of the measuring instrument.it can be used to judge an instrument which is precise.
deepesh0October 1, 2003 at 9:16 pm #90527
S.LipscombMember@S.Lipscomb Include @S.Lipscomb in your post and this person will
be notified via email.If the standard deviation is the same for two sample populations, such as in a reproducibility study between two different instruments, and the mean is significantly different (i.e., it is shifted or biased along the number line), it seems to me that Cv as a “measure of relative scatter in comparing data” is useless. Please, help me understand your point. Thanks.
0January 10, 2007 at 6:41 pm #150248No offers any concrete explanation of the meaning of this measure. All explanations evolove around the vague textbook description that is hard to understand anyway. If COV is a measure of dispersion, and so do the standard deviation, what is the difference between the two? Why not we just use the SD as cov itself is based on SD?
Any good explanation is gratefully acknowledged!!
Mahal0January 10, 2007 at 7:35 pm #150249
Brian PParticipant@BrianP Include @BrianP in your post and this person will
be notified via email.Is there no end to the nonsense that six sigma keeps introducing ? No wonder so many six sigma companies are failing.
Control chart limits should always be 3 sigma.0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.