X bar and R charts
Six Sigma – iSixSigma › Forums › Old Forums › General › X bar and R charts
 This topic has 10 replies, 8 voices, and was last updated 15 years, 7 months ago by tbatson.

AuthorPosts

October 11, 2006 at 2:00 pm #44858
FlaviusParticipant@Flavius Include @Flavius in your post and this person will
be notified via email.Can anyone explains why in X bar and R charting, R charts work too? I know about X bars work due to cental limit theorem, however I do not understand how come samples R distribution is supposed to always follow a normal one and therefore same actions that apply to X bar charts apply to R charts?
Thanks.
Flavius0October 11, 2006 at 2:12 pm #144531Xbar provides insight on ‘between’ sample variation and
Rchart provided insight on ‘within’ sample variation.
Hope this explaination is enough.
Monk0October 11, 2006 at 2:21 pm #144534
Ken FeldmanParticipant@Darth Include @Darth in your post and this person will
be notified via email.I would suggest that you do a little reading of the work by Dr. Donald Wheeler. He will dispel your assumption that Xbar R charts work because of the Central Limit Theorem. That’s a bogus assumption. Ranges do not follow a normal distribution. The use of the WE rules should be applied to the Xbar chart. Out of control signals are good for the R chart with any other rule very carefully applied if at all.
0October 11, 2006 at 6:47 pm #144559
FlaviusParticipant@Flavius Include @Flavius in your post and this person will
be notified via email.Darth, thank you for reply.
I did not say that R charts as parts of X bar and R charts work because of central limit theorem. I only said about X bar charts work because of central theorm, at least this is written in ASQ CQE, CSSGB and other reference materials.
Please read more carefully before answering.
My question was if someone could explain why the distribution of samples ranges follow also a normal distribution in control charting and therefore the same out of control rules apply as for X bar.
Thanks.
Flavius
0October 11, 2006 at 6:59 pm #144560Flavious,
Please reread Darth’s reply and you will get your answer. But I will repeat it. The distribution of range samples DO NOT follow a normal distribution. The zones test should not be applied to the range chart. And please do follow his advise and read Dr. Wheeler. He will explain why it is not the central limit theorem that makes the Xbar chart work.
Bill0October 11, 2006 at 7:15 pm #144561How wonderful that people are starting to read Wheeler !!! … the undeniable expert on SPC.
Be aware of his views on Six Sigma … “the sooner one wakes up (that six sigma is rubbish) … the sooner one can begin to compete”0October 11, 2006 at 7:25 pm #144563
Ken FeldmanParticipant@Darth Include @Darth in your post and this person will
be notified via email.Bill, thanks. I must have used too many words and rambled a bit. Your succinct explanation covered it well.
0October 11, 2006 at 8:54 pm #144569Carl,
Unfortunately, I haven’t read Wheeler’s views on Six Sigma. I would definitely like to look into it though. Can you suggest any reference materials for me to read?
As you stated, he is “the undeniable expert on SPC”. Although many may disagree, maybe he is correct up to a point “that Six Sigma is rubbish”. I have to see his reasoning for stating such.
Chris0October 11, 2006 at 10:06 pm #144573
FlaviusParticipant@Flavius Include @Flavius in your post and this person will
be notified via email.Guys, thank you all for posting, I appreciate you answers.
Cheers.Flavius0October 12, 2006 at 5:15 pm #144634
Dr. Mikel HarryMember@MikelHarry Include @MikelHarry in your post and this person will
be notified via email.R chart focuses on within sample variation
X chart focuses on between sample variation
Put focus first on R chart before the X chart0October 12, 2006 at 6:43 pm #144642Mikel,
I am trying to develop a R Chart and XBar chart. Do you know where I can get examples of good quality charts?
Thanks,
0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.