What is Cgk? (Index of Testing Means Capability)

[Atul Khandekar]

Can anyone point to any references about what exactly is Cgk (Index of Testing Means Capability) and how is it calculated?

I found only one reference to it on the web at http://www.csigmbh.de (Sorry, I don't remember the complete URL of the page right now)

Thanx in advance.

Atul Khandekar

Atul,
In a previous employment we used to calculate Cg which was done by comparing six standard deviations (from the measurement system) to one tenth of the process specification limits.
(tolerance/10)/(6*SD of measurement system).
I guess if you used a traceable master to do your study, you could then apply +/- one fifth of the spec to produce an upper and lower limit. Then calculate Cgk upper & lower using 3 SD's as in Cpk calcs.
-for instance Cgk upper = "Upper Limit"-trial mean/ (3* trial SD)

Seems like a lot of effort to produce a capability index that no-one recognises though!
Cheers

Brian
I think the old (outdated) Ford R&R manual had details on this.

[Marc]

From: Tomo Doran
Newsgroups: misc.industry.quality
Subject: Re: What is Cgk?
Date: 29 Mar 2000 03:51:31 GMT

The capability indices Cg & Cgk are related to gaging and compare the variation and location to a reference figure - often 10% of process tolerance in the same way that Cp & Cpk is derived.

Let me know if this helps or you want more information

[Marc]

Does anyone have any contemporary information / comments on Cgk (Index of Testing Means Capability)?

[Miner]

There is not much information available on this topic, which means that it never really took off.

The short story is:

Cg = 0.2 * StDev(Process) / StDev(Gage)

and

Cgk = [3 * StDev(Process) - |Bias|] / [3 * StDev(Gage)]

Cg is really rendundant if you have %GRR. It adds no new information, just packages it differently. Cgk is only of use if you did not establish credible calibration acceptance limits. If that was done, Cgk adds little value.

[Ajit Basrur]

There is some info on CgK in one of the older posts - Cgk - The Kolmogoroff Method

[Atul Khandekar]

Ah..that was my first post at the Cove!

Miner is right. It is one way of calculating measurement capability index.
Also: http://elsmar.com/Forums/showthread.php?t=12061

[Ajit Basrur]

Originally Posted by Atul Khandekar

Ah..that was my first post at the Cove!
Miner is right. It is one way of calculating measurement capability index.
Also: http://elsmar.com/Forums/showthread.php?t=12061

Oh, you still remember it