Gage R&R Short Study vs. Long Study vs. Other Studies

MasterBB

Involved In Discussions
#1
In Gage R&R; there are many experts including the AIAG source suggesting the short method (5 parts x 2 operators x 2 replicates) = 20; I don't think this is a statistically robust strategy. It maybe good enough as a starting point that will lead to a different Gage RR Strategy.
And there is also, the Long Method: (10 parts x 3 Operators x 3 Replicates) = 90. This sounds like a good strategy if you have the time/resources @ your disposal.
I am seeking your help & advice as what strategy would you follow, recommend, has worked for you in the past. In another word; what is the min # of parts, opertors, & replicate that you recommend.
Note: The study has to achive the objective of a Gage R&R study & to qualify the Gage, and be Statistically Robust & sound.

Any recommendations, guidance, a formula, a stratergt that have worked with you would be appreciated.

Thanks in advance
 
Elsmar Forum Sponsor

Bev D

Heretical Statistician
Staff member
Super Moderator
#2
Re: Short Study vs. Long Study vs. Others

There are several posts on this issue and a search may yield some interesting thoughts as well. Also read Miner's blogs on R&R - they are very good.

My opinion is that the AIAG sample plan - both long and short - is flawed. The fundamental reason is that Gage R&R studies are intended to estimate measurement error in it's many component forms. Measurement error is a standard deviation, it is not an average. The sampling error for standard deviations is much more variable than that for averages, additionally, it is not symetrical, it is skewed to the large side. Therefore sample sizes required for accurate estimates of a standard deviation are larger than for an average.

In the case of R&R studies there are two sample sizes that are involved: the repeatability size (AIAG calls out n=3) and the number of repeatability samples (AIAG calls out k=5 for the short and k=10 for the long)

When estimating a standard deviation there is very little accuracy gained in increasing the (replicate) sample size form n=2 to n=3, even if you calculate the standard deviation of the replicates instead of the Range as most spreadsheets do. So I use only n=2 for the repeatability sample size.

On the other hand the number of replicate samples has a large effect on accuracy if you increase from k = 5 or 10 to k = 30. This is particularly helpful when estimating the product standard deviation in order to un-confound the components of variation....think about 5 samples that span the range of product variation and 30 samples. which one do you think will provide a better estimate?? (try it in EXCEL...)

At n=2 and k=30 we still have a manageable overall sample size but much better accuracy in our estimates...
 

MasterBB

Involved In Discussions
#4
Thanks Bev & Mark.

The ISO-PLOT approach as dicussed by Miner is a good approach & I think it's part of the tools used within RED-X Techniques. The output is a Discrimination Ratio = Product Variation / Measurement error.

Have you came across an ISO-PLOT Excel Template?

Thanks in advance.:thanks:
 

Miner

Forum Moderator
Staff member
Admin
#5
If you open the MSA 3rd ed.xls file in my blog, and open the tab GRR MSE Graphs, you will see an Intraclass Correlation plot. The source data is on a hidden worksheet called Graph Worksheet.

This is the basis for an ISO-Plot. You can easily convert this to an ISO-plot by adding the 45 degree line. It also calculates the Discrimination Ratio.

And you are correct. Dorian Shainin did advocate the ISO-Plot used in Red-X techniques as their version of an MSA.
 

bobdoering

Stop X-bar/R Madness!!
Trusted Information Resource
#6
A key factor in the validity of the Gage R&R is the number and choice of the operators. I suggest three at a minimum for operator-influenced gages: a very qualified person, a moderately qualified person (perhaps shop floor with experience) and the least qualified operator that would ever use the gage. From that, you will know how much operator effect you will have on the measurement system. It should also qualify the system for any operator that meets those qualifications, negating the need for annual gage R&R assessment. Gage R&R does not have a time function, but if - over time - you change the system by bringing in lesser qualified operators than the original participants, then you would need to re-qualify the system.

Be careful when using automated gages that you do not underestimate the effect of the operator. You may find that loading specimens, for example, may influence the system.
 

MasterBB

Involved In Discussions
#7
Thanks Miner for the response.

I've noticed that your DR being > 7 is differnt than the RED-X (which is 6) for the measurememnt to be Good.

What is the differnce?

Thanks
 

Bev D

Heretical Statistician
Staff member
Super Moderator
#8
Shainin did call the square scatter plot with a 45 degree line an "Isoplot" and I believe he service marked the name.

HOWEVER, the plot itself was first published by Jack Youden in 1959: Youden, William John, “Graphical Diagnosis of Interlaboratory Test Results”, Industrial Quality Control, May 1959, Vol. 15, No. 11

It is commonly refered to as a "Youden Plot"

the Intraclass Correlation Coefficient is a standard statistic for matched pairs such as for measurement error.

There is no mathematical basis for a minimum Discrimination Ratio. It is based on empirical experience for PROBLEM SOLVING. so different individuals like to 'require' different minimum values...

I have also attached the spreadsheet I use. It plots the spec limits and the 45 degree line and will provide a square printout
 

Attachments

Miner

Forum Moderator
Staff member
Admin
#9
Thanks Miner for the response.

I've noticed that your DR being > 7 is differnt than the RED-X (which is 6) for the measurememnt to be Good.

What is the differnce?

Thanks
I used the guidelines advocated by Donald Wheeler, which he originally promoted independently of any graphical analysis.

And Bev D is correct. Youden originated the Youden Plot, which originally had a mainly graphical interpretation focused on looking for outliers and evidence of bias between different laboratories. Shainin later adapted it for use as an early MSA tool in his Red-X methods using repeated measures of the same gauge and comparing the ratio of part variation to repeatability variation. Shainin emphasized simple methods that were light on statistics to encourage use by the statistically challenged.
 

MasterBB

Involved In Discussions
#10
Bev & Miner,

Thanks a lot for the info/files..

Is L37 in the work sheet is basically my Gage Sigma?

---------------
Another question:
Trying to utilize historical data for a gage (Tester)... The data is not balanced/structured properly per the Stanadard/Minitab...

The question if I utilize the data as-is & include multiple operator; What's the best way to calculate my Gage Variance?

The data that I am dealing with is kind of tricky because it's not a static dimension... It's a dynamic behavior & hence it adds complexity.

I would like to pass this approach by you...
What about utilizing a General Linear Model & analyze Operators & the Parts as inputs (unbalanced data)... The output is an ANOVA table with S, R-sq, and adjusted R-squre....

Is it safe to say that S is actually my Sigma for my Gage?

What's your thought???

I could not use the ISO Plot as my data is destructive unless I assume homogenousity....

Also, refresh my memory: In Iso-plots: Do I have to use a different operator for Measurement #2? Or one operator is OK for borh measurements?


Thanks in advane..
 
Thread starter Similar threads Forum Replies Date
A GR&R (Gage R&R) - MSA - Section 6 Attribute Gage Study - Short Method Requirements Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
P Long and Short (Variable Data) Gage Studies - Urgent Help needed Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
T Plug Gage Calibration Calibration and Metrology Software and Hardware 1
L Gage R&R TMV Acceptance Criteria Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
S MSA for attribute relation gage Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
E Zero part to part variation - Gage R&R project Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 15
M Gage R&R and right way to measure Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 16
L Gage RandR on automated equipment. IATF 16949 - Automotive Quality Systems Standard 7
B Gage calibration frequency, ISO and IATF - What are the requirements Calibration Frequency (Interval) 3
D Difference between Test Method Validation and Gage R&R Qualification and Validation (including 21 CFR Part 11) 18
R Determining Uncertainty from Gage R&R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1
C Correct Calibration Method for Dial Depth Gage General Measurement Device and Calibration Topics 6
C Gage Block Wringing General Measurement Device and Calibration Topics 3
B Gage R&R with NDC=1 Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 19
S Type 1 Gage R&R or something else? Reliability Analysis - Predictions, Testing and Standards 6
G Should I perform Gage R&R only at the beginning of a new project? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
V Thread Plug Gage Pitch GO Diameter out of spec AQL - Acceptable Quality Level 8
G Gage R&R - Where am I going wrong? Part of a FAIR submission (Aerospace) Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
R Gage R&R Excel templates Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 3
K Gage R&R with more than 3 appraisers Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
Anerol C Gage R&R Template AIAG 4th Edition IATF 16949 - Automotive Quality Systems Standard 3
T Attributes SPC study - Attributive control (Go gage) Statistical Analysis Tools, Techniques and SPC 5
S Capability or Gage R&R Study for Leak Tester? Reliability Analysis - Predictions, Testing and Standards 15
N % Tolerance - Type 1 study on the gages, then a gage R&R (ANOVA) Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
M Definitive answer on Type 1 vs Type 2 vs Type 3 Gage Study Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 0
V Gage Management and Gage R&R Software General Measurement Device and Calibration Topics 1
D Gage R&R Study on Load Cells - Large chemical blending tanks IATF 16949 - Automotive Quality Systems Standard 1
B Minitab Type 1 Gage Study on True Position Question Measurement Uncertainty (MU) 1
S Gage R&R on alloy Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 10
8 Need Help - Runout - Function Gage Inspection, Prints (Drawings), Testing, Sampling and Related Topics 7
L Gage R&R studies for identical Devices - Need to confirm the requirement to perform them Reliability Analysis - Predictions, Testing and Standards 2
G Stab Pin Size For Check Gage Inspection, Prints (Drawings), Testing, Sampling and Related Topics 3
E Functional Gage for TOP applied at RFS Design and Development of Products and Processes 5
F No reproducibility Error in Gage R&R? Reliability Analysis - Predictions, Testing and Standards 4
M Template for Attribute Gage R & R wanted Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 3
G Warning about Deltronic Gage Pins - The "Certification of Accuracy" document General Measurement Device and Calibration Topics 13
A Gage type 1 study on CMM Capability, Accuracy and Stability - Processes, Machines, etc. 2
Q Gage R&R for Instant Measurement Machine Manufacturing and Related Processes 6
M Gage R&R with large inter part variance - Torque Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 7
D Do we need normal data for gage r&r studies? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
D Do I need part variation while doing Destructive Variable Gage R&R MSA study Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 19
S Gage R&R Standard Deviations Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 6
J Informational Gage R&R: Swapping operators Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
S Gage R & R for large amount of inspections IATF 16949 - Automotive Quality Systems Standard 10
S Ring Gage Thermal Expansion General Measurement Device and Calibration Topics 4
L Gage R&R for test precision or uncertainty prediction? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
S Minor diameter of threaded ring gage General Measurement Device and Calibration Topics 1
A Does Torque Gage Need Validation? Reliability Analysis - Predictions, Testing and Standards 4
J Ignoring a Failed Gage R&R and upcoming external audit IATF 16949 - Automotive Quality Systems Standard 22
R Scaling a Gage R&R - 2 holding fixtures each with 10 nests Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 7

Similar threads

Top Bottom