cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
The Discovery Summit 2025 Call for Content is open! Submit an abstract today to present at our premier analytics conference.
Choose Language Hide Translation Bar
View Original Published Thread

How to use ±3 sigma control limits in JMP charts

JMP The main way to create a control chart in Control Chart Builder no see .properties of data ( continuous / categorical, etc. ) If you specify correctly JMP automatically creates a control chart in .

 

but , One thing you need to know is that JMP The control limits provided by 3 Not a sigma control limit . JMP The management limits provided by Moving Range We provide management limits according to ( Please refer to the link below ).

 

Control Limits for Individual Measurement and Moving Range Charts

 

In fact, one of the questions that many people ask is why default which is given as data of sample standard deviation (s) use ( i.e. ± 3 Use of sigma control limits ) without doing Moving Range It is whether to obtain the control limit from .

this is , It would be good to note that the reason is .

 

  1. When the first control chart was actually developed (1920 years Bell in the lab Walter A. Shewhart invented by ), While managing a lot of data manually chart and , Each representative value ( Average / dispersion, etc. ) It was difficult to obtain by hand . 1920 In the 1980s, there were no computers or even calculators. It's time .
  2. In addition sample standard deviation Finding the sigma control limit by using it is assuming the normality of the data. , Actual control chart data time-dependent Therefore, it is difficult to say that normality is satisfied. .
  3. For the same reason as above moving range Estimates obtained using ( Convenience of calculations & No need to make distribution assumptions robust box ).

 

However , must be ± 3 If you want to draw a sigma control limit, you can use the following method. . example is JMP Sample Data Table sign Diameter (Sample Data middle Quality Control is in the folder ) I will show you as an example .

 

open the data , Please select the menu as follows .

Analyze >> Quality and Process >> Control Chart >> I/MR Control Chart

 

undefined

 

When the following dialog box appears Diameter cast Y select on

 

undefined

 

 

The control chart below is mentioned Moving Range This is the result showing the management limit of . To change this part, click the red circle in the upper left corner of the figure below. Red Triangle select Show Control Panel Please select the menu .

 

undefined

 

 

When the Control Panel appears, Limits A selection box will appear where you can set .

from below Levey Jennings Please select .

 

undefined

 

 

The final result is below . as you can see Levey Jennings Management limits were set using the method , The method is looking for ± 3 sigma It is a management limit. . Levey Jennings Please refer to the link below for this .

 

Levey-Jennings Charts

 

undefined

 

 

This post originally written in Korean and has been translated for your convenience. When you reply, it will also be translated back to Korean.

Comments
ChulHee_JMP
Staff

유용한 내용의 정리 및 대안 제시에 감사합니다!

 

제 의견을 추가하고 싶습니다.

"I-MR관리도의 I관리도나, Xbar-R관리도의 Xbar관리도에 대한 관리한계는 +/- 3 시그마에 설정된다"고 표현하는 경우도 종종 있습니다. 이런 경우는 '3시그마'가 '추정된 표준편차에 3배를 한 값'을 의미하겠습니다.

여기서 '추정된 표준편차'를 계산할 때에 전통적으로 Moving Range와 Range를 각각 이용해 왔습니다.

그런데 때때로 이들 관리한계를 위의 전통적인 추정 방식이 아닌 표본 표준편차 s,

즉, 아래의 산출식을 통해 추정하여 관리한계선을 설정하고 싶어하시는 분들도 있습니다. 

chulhee_min_jmp_1-1582530707723.png

그런 경우에는 이 블로그의 글로 제시된 방법을 사용할 수 있겠습니다.