Convincing Management Cpk without Stability is Meaningless

#1
I am facing a situation where my predecessor has adopted a practice of ignoring out of control conditions if the process has a high Cpk. Everything I know tells me that without stability the Cpk is meaningless but I cannot convince management of this. Knowledgeable input on this is sought. Thanks in advance :bonk:
 
Elsmar Forum Sponsor

Steve Prevette

Deming Disciple
Staff member
Super Moderator
#2
Re: Cpk without stability

I usually have good effect with pointing out that SPC is a Prediction of Future Performance. If the data prove to not be stable, they aren't predictable. If I can't predict future results, then the CpK is also meaningless in that current lucky results don't guarantee or even predict future results - that is - the likelihood of making acceptable product.
 

rmf180

Involved In Discussions
#3
Re: Cpk without stability

You are absolutely correct in stating without stability, capability is questionable. This all comes from the "is it in specification" mindset. When using SPC, it is imperative to get the folks to understand the purpose of SPC is to remove the need for 100% inspection. If all we care about is "is it in spec", then we need to ask ourselves how can we trust anything less than 100% inspection. :bonk: I would suggest explaining that SPC is based upon the normal distribution. A process which is not in control is not following the normal distribution. There are also situations where you may be better off to transform the data (destructive testing, GDT, etc) so that the control indicators are not providing false alarms.

The key is that management must understand that the process is speaking to you when you see out of control conditions. It is easier to react when parts are still in spec compared to conducting root cause analysis for a product failure in the field. Pay me now or pay me later!:deadhorse:
 

Steve Prevette

Deming Disciple
Staff member
Super Moderator
#4
Re: Cpk without stability

RMF180 - good post, though I do want to question your statement " process which is not in control is not following the normal distribution."

There are plenty of processes and their resulting data that are indeed in control, but do not follow the normal distribution. There are also data sets that follow the normal distribution, but the time series plot of the data are not in control.

Another good discussion to have is the Taguchi loss function versus simply making parts that are "in specification".
 
D

deven_17

#5
I am facing a situation where my predecessor has adopted a practice of ignoring out of control conditions if the process has a high Cpk. Everything I know tells me that without stability the Cpk is meaningless but I cannot convince management of this. Knowledgeable input on this is sought. Thanks in advance :bonk:
Hi,

Can you tell us, on how much Cpk the process is running? Its true that Cpk is meaningless without stable process but Cpk graph can only tell whether distribution is Normal or Positive skewed or negative one. Finally, then action is required to bring it to the mean..

In our company, our motive is to remove Cpk studies by stabilizing a process to lesser control limits. Then just Sampling inspection suffice the purpose.
Also, Higher Cpk also suggest Over Processing - a Waste (LEAN)

Thanks,
Deven Malhotra
 

rmf180

Involved In Discussions
#6
Re: Cpk without stability

Steve, thanks for clarifying. I agree that many processes do not follow the normal distribution, but their control indicators would indicate that they are in control. I also try to get people to understand that the CpK of a process is a snapshot (accurate at the point of calculation) where the stability chart is live. I think too much is made of CpK and not enough about stability. I like your comment about SPC being a prediction of future performance. If the current state is unpredictable, you certainly cannot predict the next hours production!:applause:
 
D

Darius

#7
without stability the Cpk is meaningless but I cannot convince management of this.
Maybe I will say something that many won't be agree but..
Management thinker Peter Drucker is often quoted as saying that "you can't manage what you can't measure."
Drucker means that you can't know whether or not you are successful unless success is defined and tracked.
Almost 20 years ago, I was starting to work in a project to do a tool for SPC, I readed that Cpk is meaningless without stability and Wheeler in his book "advanced topics on SPC" said even that other indicators like ppk should not be used because the same condition. I also readed in an article wroted by the most recognized SPC and precontrol practitioners that even with data "fabricated" there will be still some lack of stability.

Well, ok..., so what can I report to get track of the improvement?, is better not to get track of that?:confused:

I also readed a very good article about the confidence intervals for capability indexes that showed the meaningless of calculate capability indexes without reporting sample sizes, normaly not taked in account or at least the minimum value (most of us don't like to report the smaller value).:frust:

What can make your index more stable numerically (without improvement)?, just larger sample sizes, because it takes all variation sources in account, or normalizate the data (some years ago I did a study with a sample that gave me a mean very different with 200 than with 10000 units, I used normalization methods and with the first 200 gave to me the same as the one with the bigger sample.

:truce:But If you want to convince your management, you can:
* show a book of an authority on the field "Advanced Topics in Statistical Process Control" by Donald J. Wheeler, page 197" by example
* You can show books with the formula and tell them that it take in account the mean and variation estimates, and without normality (and stability affects normality) such parameters theorically nonesensical desto the resulting formulae (capability index) the same.
 

Bev D

Heretical Statistician
Staff member
Super Moderator
#8
maybe we think about the alternate - are you sure the process isn't stable?
irrational subgrouping coupled with an incorrect chart choice can make the process appear to be unstable when in fact it is actually very stable. I always question a proclamation that an unstable process has a high Cpk. I see this frequently with non-homogenous process streams. Of course the sampling for the Cpk could be wrong as well...

is it possible for you to post your data and perhaps provide a description of the characteristic and process? it is difficult to diagnose let alone prescribe a remedy without seeing the patient...:cool:
 
Last edited:
Thread starter Similar threads Forum Replies Date
A Cosmetic Spec - Convincing Management Visual Inspection Standard is Necessary Manufacturing and Related Processes 5
Y Convincing Top Management on the Value of a Lead Auditor Course ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 9
J Software Justification in a Lean Environment - Convincing Management Lean in Manufacturing and Service Industries 12
P Convincing Suppliers to Send 8D Reports and React to Complaints in a Timely Manner Supplier Quality Assurance and other Supplier Issues 24
S Tips for convincing general labour that 100% inspection not required Various Other Specifications, Standards, and related Requirements 18
M PPAP - who me? Convincing a customer to NOT request PPAP APQP and PPAP 14
B ISO 17025:2017 risk management Risk Management Principles and Generic Guidelines 0
A Purchasing Controls on Change Management of Literature/Labeling ISO 13485:2016 - Medical Device Quality Management Systems 3
normhowe "The Problem with Quality Management: Process orientation, controllability and zero-defect processes as modern myths" Book, Video, Blog and Web Site Reviews and Recommendations 2
C SharePoint Contract Management Software General Information Resources 0
John Broomfield Five ways to botch your supplier management program Misc. Quality Assurance and Business Systems Related Topics 7
S Risk Management Review ISO 14971 - Medical Device Risk Management 4
William55401 Distributed By Product - Best Practices for Configuration Management and Purchasing Controls ISO 13485:2016 - Medical Device Quality Management Systems 0
D Reports under change management | ISO 13485:2016 & ISO 9001:2015 ISO 13485:2016 - Medical Device Quality Management Systems 3
Le Chiffre Online training available for ISO/IEC 17021-1: Requirements for bodies providing audit and certification of management systems Training - Internal, External, Online and Distance Learning 3
S Risk Management and other Files ISO 14971 - Medical Device Risk Management 8
Sidney Vianna Release of ISO 10013:2021, Quality management systems – Guidance for documented information Other ISO and International Standards and European Regulations 0
G Management Review (integrated system) Management Review Meetings and related Processes 17
M Unique Quality Management System for 2 sites ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 5
M Management review check-list Management Review Meetings and related Processes 3
silentmonkey Overall Benefit/Risk Analysis - Risk Management VS Clinical Evaluation ISO 14971 - Medical Device Risk Management 3
M EMS change management ISO 14001:2015 Specific Discussions 2
Aymaneh Medical Device Cybersecurity Risk Management IEC 27001 - Information Security Management Systems (ISMS) 2
John Broomfield CIOB - Code of Quality Management Misc. Quality Assurance and Business Systems Related Topics 1
D Big companies suffer from quality management system? ISO 13485:2016 - Medical Device Quality Management Systems 1
lanley liao What shoud i do if our company top management has been changed. Oil and Gas Industry Standards and Regulations 8
Ajit Basrur Corporate management standards ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 4
A 21 CFR 820 - Risk Management - Looking for some guidance US Food and Drug Administration (FDA) 3
John Predmore Configuration Management as a process instead of a procedure AS9100, IAQG, NADCAP and Aerospace related Standards and Requirements 10
optomist1 Informational Training IMDS - Management of Product Chemical Regulatory Compliance RoHS, REACH, ELV, IMDS and Restricted Substances 2
Pau Calvo Quality Management process is mandatory in ISO9001? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 10
S Supplier Management ISO 13485: 2016- Which supplier needs to fill in a self assessment form? ISO 13485:2016 - Medical Device Quality Management Systems 6
J Audit Checklist for Integrated Management System for ISO 9001:2015, ISO 14001 & OHSAS18001 (IMS) ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 7
Sravan Manchikanti Software Risk Management & probability of occurrence as per IEC 62304 IEC 62304 - Medical Device Software Life Cycle Processes 8
M Change management procedure when 7.3 is not applicable ISO 13485:2016 - Medical Device Quality Management Systems 5
S Management Review (9.3) - Management Review Minutes/Report ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 13
R How would you work without a quality management system? IATF 16949 - Automotive Quality Systems Standard 3
J ISO 13485 System 'soft start' - How to best reflect this in initial audits, management review minutes and other records? ISO 13485:2016 - Medical Device Quality Management Systems 3
P Conformity assessment based on a quality management system or production quality assurance EU Medical Device Regulations 3
M Management is about people? Human Factors and Ergonomics in Engineering 1
R Electrical contractor Project Quality Management Plan Quality Manager and Management Related Issues 1
S Quality management system (Well head installation & maintenance) Quality Management System (QMS) Manuals 5
G Copy of withdrawn ISO 9001:1994 Quality Management Standard ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 2
P How to develop executable quality management system for rookies? IATF 16949 - Automotive Quality Systems Standard 9
R Identify Medical Device characterstics as Annex C of ISO 14971 Risk Management ISO 14971 - Medical Device Risk Management 5
Q Example Process orientation to the process leadership, management, goals (tasks of the top management) ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 10
M Requirement to manufacture under a quality management system EU Medical Device Regulations 4
G Supplier management when the supplier is your headquarter IATF 16949 - Automotive Quality Systems Standard 3
G IMS (Integrated Management System) 9001, 14001 & 45001- Request Assistance ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 8
A IATF 16949 4.3.1 - Determining the scope of the quality management system - supplemental IATF 16949 - Automotive Quality Systems Standard 9

Similar threads

Top Bottom