Gage R & R on Visual Inspection using the Cross Tabulation Method

brandieb1230

Involved In Discussions
Hello!

I am working on conducting my first gage r & r on a visual inspection. I am using the cross tabulation method and the template I have is using 3 operators 3 times 30 parts. Is this required?

I am hoping to use 3 operators, 3 times, 20 parts (6 bad-14 good).
 

howste

Thaumaturge
Trusted Information Resource
Re: Gage R & R on Visual

Hello!

I am working on conducting my first gage r & r on a visual inspection. I am using the cross tabulation method and the template I have is using 3 operators 3 times 30 parts. Is this required?

I am hoping to use 3 operators, 3 times, 20 parts (6 bad-14 good).

In the MSA manual page 40 it says:
Sample Size

The question always arises: “How many samples should be used in the study?” To the dismay of most people, the answer is “enough”. The purpose of any measurement study (variables or attribute) is to understand the properties of the measurement system.. A sufficient number of samples should be selected to cover the expected operating range (see also Chapter II Section C). With attribute measurement systems, the area of interest are the Type II areas (see Chapter I, Section B). If the inherent process capability is good (i.e., large Cp, Cpk or Pp, Ppk) then a small random sample may not have many (or any) samples in this area. This means that as the process capability improves , the required random sample for the attribute study should become larger).
The short story is that there is no number specified. If you use a small sample you should use statistical principles to justify your sample size. You should expect some questions if you only use 20 parts.

FWIW for most attribute studies I've seen 50 parts used.
 

Bev D

Heretical Statistician
Leader
Super Moderator
Re: Gage R & R on Visual

If you are trying to comply with a Customer requirement and the template was supplied by them, I would stick to the template.

If you are trying to really understand the effectiveness of the visual inspection, then you might find this paper helpful it has a section for categorical data (visual).

A couple of points:
there is really not much value in doing the inspection 3 times for each operator & part. (other than complicating the calculations) 2 times more than sufficient.
There is a LOT of value in increasing the number parts at 20 or even 30 parts operators can remember and that really skews your analysis. The paper includes a two step process but in summary, the critical elements of the study design are that you include parts at the 'cutoff' (marginally good / marginally bad) and that the defect rate in the sample is equivalent to the defect rate being experienced in real life.
 

Ron Rompen

Trusted Information Resource
Re: Gage R & R on Visual

I agree completely with you Bev, when you say that there is really not much value in doing the inspection 3 times per inspector instead of two, and that additional samples have much more value, inparticular if they are borderline/cutoff samples.
The difficulty that I have encountered in the past is with customer requirements that are on a checkbox list; I'm sure you know the type:
GR&R done? Y/N
'n' samples? Y/N
3 operators x 3 trials per operator? Y/N
GR&R < 10%? Y/N

Too many SQA's and program managers these days dont really understand what they're looking at - they only have a shopping list to go by, and if you don't have all the items on that list (whether they are relevant or not) then you are not going to be approved.
 

Bev D

Heretical Statistician
Leader
Super Moderator
Re: Gage R & R on Visual

Too many SQA's and program managers these days dont really understand what they're looking at - they only have a shopping list to go by, and if you don't have all the items on that list (whether they are relevant or not) then you are not going to be approved.

the dumbing down of the quality profession

that's why I started with the disclaimer about customer requirements...and why I got out of automotive and aerospace so long ago :)
 
Top Bottom