Turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- Cpk Analysis

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Sep 26, 2016 12:06 AM
(13893 views)

Example Dtata |

98.8 |

99.7 |

99.7 |

99.9 |

99.5 |

100.0 |

100.4 |

98.8 |

99.3 |

100.5 |

100.4 |

100.5 |

100.2 |

100.4 |

101.5 |

100.7 |

100.7 |

100.4 |

99.7 |

100.3 |

100.4 |

101.2 |

101.2 |

100.0 |

99.7 |

100.3 |

101.4 |

101.0 |

100.5 |

Kindly Help For Above Data.

I want to find Within sigma estimated by moving range & Cpk. Please Help me.

1 ACCEPTED SOLUTION

Accepted Solutions

Highlighted
If I assume that you are dealing with a one sided specification of >98% Assay for instance I can use either Quality and Process Control Chart Builder or an IR/MR control chart under the Analyze>Quality and Process platform.

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

7 REPLIES 7

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

I may have missed it, but do you have spec limits?

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

Sprc Limit is 98 to 102.

For Within sigma JMP is using which Constant?

d2=? 1.1.28 or any other?

Highlighted
If I assume that you are dealing with a one sided specification of >98% Assay for instance I can use either Quality and Process Control Chart Builder or an IR/MR control chart under the Analyze>Quality and Process platform.

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

Thank you Mr Lou Valente For Reply.

But My Question is For Within sigma JMP is using which Constant?

d2=? 1.1.28 or any other?

@Lou Valente

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

If I may add a point here: If I assume your data is in time order (a requirement for a control chart), then you definitively have two populations in your data. The first 9 data points comprise one population and the remaining 20 points comprise the second. You can calculate Capability Indices for both populations separately, but to calculate a Capability for the entire data set is meaningless. Any process must be in a "reasonable degree of statistical control" before one can calculate meaningful Capability Indices. Your first question from this data set should be, "What happened to the process between somewhere around data points 9 and 10 that caused the process to shift upwards." If the special cause of the shift is a good thing, you need to understand what the cause is and modify the system to make this permanent.

I hope this helps.

Steve

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Cpk Analysis

For individuals/moving range charts, you should always use the following formulas for computing limits:

Limits for *Individuals chart* = *average* ± 2.66 * *average moving range*

Upper limit for *mR* chart = 3.268 * *average moving range*

*As Dr. Wheeler says in his articles on the right and wrong ways to do control charts, "Accept no other limits".*

Steve