cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
Choose Language Hide Translation Bar
Metamong
Level I

Confusion of rule 3 violation against minitab and definition

Hello, i'm JMP 17 user. I have one question.

Nelson Rule 3  (Warning-Test3) : 6 data poins in-a-row steadily increasing or decreasing

 

Metamong_0-1679649732841.png

 

definition itself is confusing and for other program (Minitab), it doesn't trigger rule 3. if i change last number 0 to 7, then it appears

 

Metamong_1-1679649964167.png

 

which one is right?

5 REPLIES 5
Victor_G
Super User

Re: Confusion of rule 3 violation against minitab and definition

Hi @Metamong,


Welcome in the Community !

Regarding the Nelson rule n°3 (and others), you can find more explanation and visualizations here : 
Nelson Rules – Lean Manufacturing and Six Sigma Definitions (leansixsigmadefinition.com)
Control Chart Thresholds (infogixsaas.com)

The definition states : "Six (or more) points in a row are continually increasing (or decreasing) (trend)". So the sixth point (and consecutive ones if the trend continues) should be highlighted, as the screenshot on JMP show it.
As I don't have Minitab, I'm not able to reproduce the issue you are showing, sorry.

I hope this answer will clear any confusion,

Victor GUILLER

"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)
Metamong
Level I

Re: Confusion of rule 3 violation against minitab and definition

Thanks for reply

 

but those two links or many examples in google also make me confused.

 

Metamong_0-1679800919406.png

 

Upper picture is mostly used but conflicted with JMP - 1 2 3 4 5 6 7* (6 increment) 

 

 

Below picutre - 1 2 3 4 5 6* (5 increment). This is same approach with JMP and i thought it is right.

But can i find exact source to prove it is right?

Metamong_1-1679800934534.png

 

statman
Super User

Re: Confusion of rule 3 violation against minitab and definition

There is confusion regarding whether the "out-of-control" condition rule 3 is dependent on Points or Posts, but it appears Minitab uses 6 as well:

 

https://blog.minitab.com/en/statistics-in-the-field/using-the-nelson-rules-for-control-charts-in-min...

 

"All models are wrong, some are useful" G.E.P. Box
Metamong
Level I

Re: Confusion of rule 3 violation against minitab and definition

Right. minitab also uses 6 but with different approach

 

6 points in a row increasing or decreasing

1 2 3 4 5 6* (5 increment) - Out of Trend for JMP

1 2 3 4 5 6 7* (6 increment) - Out of Trend for Minitab

 

Can i know which one is right based on correct source?

Re: Confusion of rule 3 violation against minitab and definition

JMP is following Nelson.  You might find the following article of interest The Ambiguous Control Chart Trend Rule | Quality Digest.  Of particular interest is this text from the article "In 1984, Lloyd Nelson added control chart rules, including the trend rule: six consecutive points increasing or decreasing.2 I suspect this rule was particularly hard to describe because Nelson included a visual representation of the rule (figure 1). Note that his written description lists “six points in a row steadily increasing or decreasing,” and each of the data sets shown in the illustration contain exactly six points. So, we can infer that Nelson’s definition of the trend rule is six points in a row steadily increasing or decreasing including the first point."