4.5 sigma Control Limits
Six Sigma – iSixSigma › Forums › Old Forums › General › 4.5 sigma Control Limits
- This topic has 17 replies, 9 voices, and was last updated 15 years, 6 months ago by
qualitycolorado.
-
AuthorPosts
-
November 18, 2006 at 8:39 pm #45279
holein1Participant@holein1Include @holein1 in your post and this person will
be notified via email.I am familiar the 4.5/6 sigma concept, but if I generate a control chart from short term data with +/- “3 sigma” control limits can someone explain why I cannot add the 1.5 sigma shift and produce along term “monitoring” type chart with control limits at +/- “4.5 sigma”
Thanks0November 18, 2006 at 9:33 pm #147460
qualitycoloradoParticipant@qualitycoloradoInclude @qualitycolorado in your post and this person will
be notified via email.Holein1- Hello!Regarding your question — I think you will find the answer at these iSixSigma.com links (quick explanations of the 1.5-signa shift and short-term vs. long-term):https://www.isixsigma.com/library/content/c010701a.asphttps://www.isixsigma.com/library/content/c010311a.asp… hope this helps …Best regards,QualityColorado
0November 18, 2006 at 11:13 pm #147465QualityColorado,
Wake up sleeping beauty. Nobody here believes that 1.5 crap. Even Harry changed his tune on the 1.5 shift about 4 years ago.0November 18, 2006 at 11:55 pm #147466BB is correct but a little blunt. Here’s the full history in brief:
Harry confuses 1.5 Shainin Pre Control green band limits with control chart limits.
Bill Smith observes “sudden shifts” due to special causes and broadens tolerances to Cp=2.
Mikel Harry derives +/-1.5 as a “shift” in the process mean, based on tolerances in stacks of disks. This is referred to as the Z shift.
Harry realises his error and says the 1.5 “is not needed”.
Harry in about 2003 makes a new derivation of 1.5 based on errors in the estimation of sigma from sample standard deviations. For a special case of 30 points, p=.95 he multiplies Chi square factor by 3, subtracts 3 and gets “1.5”. Actual factor ranges from 1 to 18. He now calls this a “correction”, not a “shift”.
Reigle adds a new calculation he calls a “dynamic mean off-set.”: 3 / sqrt( n ) where 3 is the value for control limits and n is the subgroup size. For n=4 he gets “1.5”. Reigle says “This means that the classic Xbar chart can only detect a 1.5 sigma shift (or larger) in the process mean when subgroup size is 4”. Reigle is quite incorrect. Such data is available from ARL (Average Run Length) plots.
In other words, there is no 1.5. There is no 3.4. Six sigma tables are nonsense. Forget about 1.5.
Control limits are always +/-3 sigma.
0November 19, 2006 at 12:14 am #147467
qualitycoloradoParticipant@qualitycoloradoInclude @qualitycolorado in your post and this person will
be notified via email.Holein1,As BB points out in his reply to your post, there is considerable debate regarding whether the 1.5-sigma shift is useful (or even advisable to use). It is definitely controversial.Dr. Don Wheeler, a well-respected statistician, calls the Six Sigma shift “goofy” (see: http://en.wikipedia.org/wiki/Six_Sigma). More of Dr. Dr. Wheeler’s comments can be found in the free white paper from his site: http://www.spcpress.com/ink_pdfs/The%20Final%206%20Sigma%20Zone.pdf.Dr. Tom Pyzdek, another well-respected member of the Six Sigma community, has some interesting thoughts about the shift — see this article: http://www.qualitydigest.com/may01/html/sixsigma.htmlAs Dr. Pyzdek note, ” The 1.5 sigma shift is simply a correction that accounts for factors not included in our model of reality”. Whether the 1.5 sigma shift is something that helps you model your reality is something you will need to determine.Nevertheless, many Six Sigma courses still teach it, and ASQ’s “Body of Knowledge” also still refers to it (http://www.asq.org/certification/six-sigma-green-belt/bok.html) so, you may need to know how to deal with it in your control charting and certification testing…. hope this helps …Best regards,Quality Colorado
0November 19, 2006 at 12:55 am #147470
Bash Me TooParticipant@Bash-Me-TooInclude @Bash-Me-Too in your post and this person will
be notified via email.BB:
In what publication did Harry “confuse” the 1.5 shift with Shannin rules, or is this just more of your “feelings”? I would like to read that report.
In what publication did Bill Smith provide his reasoning of “sudden shifts.” I would also like to read this report.
I recall reading where Harry said the 1.5 shift “is not needed,” but you did not provide the entire quote, only that portion you want to post, perhaps to make a hollow point. Why don’t you post the entire quote, not just what you want people to see?
Seems you are taking things out of context from what was originally published. This is the way of bashers. They love to misquote people for personal reasons, usually related to ego building or jealousy.1November 19, 2006 at 12:59 am #147471
Bash Me TooParticipant@Bash-Me-TooInclude @Bash-Me-Too in your post and this person will
be notified via email.Quality Colorado:
Great response!!!0November 19, 2006 at 2:05 am #147476The 1.5 is pure snake oil. It doesn’t exist.
If you think it does, prove it !!!!!!!
Perhaps you might use one of Harry’s so called “studies” … without references …1November 19, 2006 at 9:47 am #147480
Marlon BrandoParticipant@Marlon-BrandoInclude @Marlon-Brando in your post and this person will
be notified via email.Agree
0November 19, 2006 at 9:51 am #147481
Marlon BrandoParticipant@Marlon-BrandoInclude @Marlon-Brando in your post and this person will
be notified via email.Congratulation for being able to bring references and apprropriate articles to support your point of view.
0November 19, 2006 at 10:04 am #147482Pyzdek’s article is a farce. He pulls 1.5 out of the air without any justification whatsoever. He still calls it a “shift” instead of a “correction”.
If the 1.5 were really a shift it would mean that every process in America was out of statistical control at least 13-14% of the time. With the idiots that are running six sigma programs, such a distasterous situation is becoming increasingly likely.
My personal view is that the 1.5 is part of a Japanese plot to destroy American industry.0November 19, 2006 at 10:26 am #147484
holein1Participant@holein1Include @holein1 in your post and this person will
be notified via email.Thanks everyone. Much appreciarted
0November 19, 2006 at 12:01 pm #147485
Marlon BrandoParticipant@Marlon-BrandoInclude @Marlon-Brando in your post and this person will
be notified via email.Really very funny?
How it comes ,when Japanese has nothing to do with SS?
They are satisfied with their TQC & TPS??0November 19, 2006 at 12:03 pm #147486
Marlon BrandoParticipant@Marlon-BrandoInclude @Marlon-Brando in your post and this person will
be notified via email.For what?
0November 19, 2006 at 12:37 pm #147487
Howling OwlParticipant@Howling-OwlInclude @Howling-Owl in your post and this person will
be notified via email.With all respect, I think the error lies with some USA academics, statisticians, and quality experts, who’ve allowed this nonesense to go unchecked.
Perhaps it’s an American plot to destroy American industry!
This is typical of what happens when people only speak to those who agree with them, and have no time for anyone who disagrees! Isn’t this what happens on Capital Hill – no wonder this nation is in such a mess!0November 19, 2006 at 3:29 pm #147492
Bash Me TooParticipant@Bash-Me-TooInclude @Bash-Me-Too in your post and this person will
be notified via email.Holein1:
Here is another site reference on the 1.5 shift. Looks pretty good to me.
https://www.isixsigma.com/forum/ask_dr_harry.asp?ToDo=view&questId=18&catId=60November 19, 2006 at 5:39 pm #147494
B WestlakeParticipant@B-WestlakeInclude @B-Westlake in your post and this person will
be notified via email.Dear Thick as Two Planks,
The Japanese don’t use SS because they know its a fraud.1November 19, 2006 at 7:06 pm #147497
qualitycoloradoParticipant@qualitycoloradoInclude @qualitycolorado in your post and this person will
be notified via email.Hole-in-1:You are welcome! Best wishes for every success on your Six Sigma journey.Best regards, QualityColorado
0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.