p-Value(s) for Anova (Crossed) GRR (Gage R&R) Studies

S

straetfeild

#1
Good day all,

I've had discussions with colleagues of mine here at work debating whether or not an acceptable p-value is required to use a given set of data for a GRR study (10*3*3). I can't find where MSA or any other documented parameters require me to do so. The experience of one of my peers is that his customer (a Big-3 automotive manufacturing company) required this in person, so we should have this as our standard accross the board.

Mathematically speaking, does an unacceptable p-value (p>0.05) automatically render the data unacceptable for an ANOVA-crossed GRR, and if so, is the reason because it is an ANOVA-based study?

I appreciate any advise and/or thoughts you may have, and I apologize in advance for any breach in established posting protocol.

(Edit: I tried to copy-paste the data, but was unsuccessful.)

Thanks!
 
Last edited by a moderator:
Elsmar Forum Sponsor

Miner

Forum Moderator
Staff member
Admin
#2
I love this question. This is the first NEW MSA question that I have seen in a long time.

To start, the current MSA methodology as defined by AIAG, endorsed by the automotive industry and codified by the statistical software companies totally ignore the p-values with one exception.

That exception is for the Operator x Part interaction. In Minitab, if the Op x Part interaction p-value is greater than 0.25 (default value), the interaction is then pooled with the ANOVA error term thus becoming part of Repeatability. If it is less than 0.25, it is shown separately as a sub-item under Reproducibility. Why 0.25? Minitab says to stay consistent with AIAG. AIAG wanted to be extremely conservative about pooling the interaction in error.

Technically, if the Reproducibility p-value is greater than alpha (usually 0.05), it also should be pooled into the error term becoming part of Repeatability. It is only when it is less than alpha that Reproducibility can be distinguished from Repeatability. However, AIAG is silent on this matter and the canned MSA routines in software do not allow it. To do it yourself, you would have to run the standard ANOVA routines and manually generate the graphs.

The p-value for Parts also provides information. If the p-value of Parts is greater than alpha, the part variation is indistinguishable from Repeatability variation. If the p-value is less than alpha, the gage can distinguish at least one part as different from the rest. Not definitive that the gage is good (p < alpha), but conclusive that it is not good (p > alpha).

Thank you for this question.
 
P

Piotr Stoklosa

#3
Why 0.25? Minitab says to stay consistent with AIAG. AIAG wanted to be extremely conservative about pooling the interaction in error.
Does it mean that 0.25 is another rule of thumb? Or maybe it has any statistical background? Sometimes I suspect that it has something to do with alpha level: because the interaction is part * oper, so it's like squaring 0.05 * 0.05, but it gives only 0.0025, not 0.25.
 

Miner

Forum Moderator
Staff member
Admin
#4
It does have something to do with alpha. AIAG has arbitrarily established an alpha = 0.25. This means that there is a 25% chance that if the null hypothesis (there is no interaction) is correct you will mistakenly reject that hypothesis in favor of the alternate hypothesis (there is an interaction).

I strongly disagree with this approach. The alpha risk for the interaction should be the same as for the operators.
 
P

Piotr Stoklosa

#5
Good news for everyone. In Minitab 17 they lowered default "alpha to remove interaction" to 0,05 which is now explicable with CI :).

To Miner: In your previous message you say that AIAG requires 0,25 (I can't find a source of this information, whould you be so kind to give me the reference?). Does it mean that AIAG changed its mind and accepted recognized statistical approach?

Thank you for comments.
 

Miner

Forum Moderator
Staff member
Admin
#6
I took a quick look through the MSA manual versions 3 & 4 and could not find anything either. I cannot remember whether this was in an earlier version and was dropped, but it appears to be a non-issue now.
 
G

G.Pito

#7
I love this question. This is the first NEW MSA question that I have seen in a long time.

To start, the current MSA methodology as defined by AIAG, endorsed by the automotive industry and codified by the statistical software companies totally ignore the p-values with one exception.

That exception is for the Operator x Part interaction. In Minitab, if the Op x Part interaction p-value is greater than 0.25 (default value), the interaction is then pooled with the ANOVA error term thus becoming part of Repeatability. If it is less than 0.25, it is shown separately as a sub-item under Reproducibility. Why 0.25? Minitab says to stay consistent with AIAG. AIAG wanted to be extremely conservative about pooling the interaction in error.

Technically, if the Reproducibility p-value is greater than alpha (usually 0.05), it also should be pooled into the error term becoming part of Repeatability. It is only when it is less than alpha that Reproducibility can be distinguished from Repeatability. However, AIAG is silent on this matter and the canned MSA routines in software do not allow it. To do it yourself, you would have to run the standard ANOVA routines and manually generate the graphs.

The p-value for Parts also provides information. If the p-value of Parts is greater than alpha, the part variation is indistinguishable from Repeatability variation. If the p-value is less than alpha, the gage can distinguish at least one part as different from the rest. Not definitive that the gage is good (p < alpha), but conclusive that it is not good (p > alpha).

Thank you for this question.
sorry for being a little late with my reply (only 15 years) :)

I have a question: why did you write "AIAG wanted to be extremely conservative about pooling the interaction in error."?

On AIAG MSA 4th edition, page 198 (referring to the example case study) it looks like they pooled the interaction in Appraiser-by-part , but then, considered that the F Ratio was far lower than the F critical (for Alfa 0.05, df1=18, df2=60) they pooled it in error.

Am I wrong?
I apologize for this "stupid" question (I'm a newbie) but it is just to understand...

Thank you in advance
(waiting for you reply in 15 years ah ah)
 

Miner

Forum Moderator
Staff member
Admin
#8
I have a question: why did you write "AIAG wanted to be extremely conservative about pooling the interaction in error."?

On AIAG MSA 4th edition, page 198 (referring to the example case study) it looks like they pooled the interaction in Appraiser-by-part , but then, considered that the F Ratio was far lower than the F critical (for Alfa 0.05, df1=18, df2=60) they pooled it in error.
In normal practice (using ANOVA), you would not show an interaction unless it were statistically significant (p < 0.05). So, by default the interaction is not shown unless p < 0.05. AIAG drastically loosened the requirement for statistical evidence by showing the interaction unless the p >0.25.

I originally wrote this post when the 3rd edition was current. The example you cite was revised for the 4th edition adding the pooling portion (Maybe someone at AIAG read my post?).
 
Thread starter Similar threads Forum Replies Date
R P-value and interpretation of ANOVA Gage R & R Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 11
M Calculating P-value for one way Anova test Statistical Analysis Tools, Techniques and SPC 3
M Determining a tolerance value for Measuring devices in-house inspection General Measurement Device and Calibration Topics 12
Proud Liberal Improving low p-value Statistical Analysis Tools, Techniques and SPC 13
BeaBea Registrars with VAR (Value Added Reseller) experience Registrars and Notified Bodies 8
qualprod Best approach to get a real value as average? Statistical Analysis Tools, Techniques and SPC 6
F Missing value of Uncertainty B Measurement Uncertainty (MU) 10
F Calibration certificate content - Average Value and True Value ISO 17025 related Discussions 6
S In BAC5300 we have machining mismatch allowed is 3tau, what is the value of tau? Document Control Systems, Procedures, Forms and Templates 1
S Change value of target during a batch Capability, Accuracy and Stability - Processes, Machines, etc. 0
A Acceptance p-value for linearity and bias analysis in minitab results Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 0
A Torque Value for Different types of Fasteners (Socket Head, Button Head, CSK) Manufacturing and Related Processes 2
M IATF 16949 - 8.5.6.1.1 Providing a list of process controls: Does this requirement add value to QMS? IATF 16949 - Automotive Quality Systems Standard 4
qualprod Cycle times, value stream mapping, inventory, average values? Lean in Manufacturing and Service Industries 1
Ashok sunder What are the criteria for setting a target KPI value against a quality objective? Benchmarking 7
S Adding Value prior to signing EASA Form 1 EASA and JAA Aviation Standards and Requirements 5
M Creating a Plant Level Value Stream Map Process Maps, Process Mapping and Turtle Diagrams 1
A IMDS - Changing the Locked Weight Value RoHS, REACH, ELV, IMDS and Restricted Substances 1
T Value Chain Map for Food Services Industry Service Industry Specific Topics 1
O P-Value less than 0.05. but everything else in control Statistical Analysis Tools, Techniques and SPC 19
qualprod P x I = Value interpretation for residual risk? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 1
O CPK with a P value less than 0.005 Manufacturing and Related Processes 8
G What degrees of freedom means in uncertainty budget and how do I set the value Measurement Uncertainty (MU) 2
Q Really do they add value (Vision, Mission, Values)? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 1
D What is the exact Temperature Coefficient Value to be set on a Conductivity Meter? General Measurement Device and Calibration Topics 2
M Value Stream Mapping Calculations Process Maps, Process Mapping and Turtle Diagrams 5
L How to interpret the average R bar Value shown in the R Chart Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2
G Non Value Added Corrective Actions IATF 16949 - Automotive Quality Systems Standard 15
R How To Calculate & Print CDF and Lower Bound CDF value for some t(time) with Minitab? Using Minitab Software 1
P Purpose of calculating Uncertainty value in calibration study Measurement Uncertainty (MU) 5
J Agenda of Value Stream Mapping workshop required Quality Tools, Improvement and Analysis 1
M What is the value of documenting in-process rework for easily-detectable issues? Quality Manager and Management Related Issues 4
R VSM - Value Stream Mapping (catheter manufacturing unit) Customer Complaints 10
W Quality for value adding or certification? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 23
T Cpk for 0 as Ideal Value Statistical Analysis Tools, Techniques and SPC 1
dubrizo Internal Audit Value - What is the point of conducting internal audits to a checklist Internal Auditing 40
L 5 minutes only for this Survey on the Value of PDCA and Your EMS Miscellaneous Environmental Standards and EMS Related Discussions 1
M How calculate P value for Linearity and Bias using Excel Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 8
J F and P-value in L9 Taguchi Design Using Minitab Software 22
S Value of Ppk or Cpk when targeting thinner material Statistical Analysis Tools, Techniques and SPC 4
B How to validate Microsoft Excel Spreadsheet Calculations for the Cpk value Capability, Accuracy and Stability - Processes, Machines, etc. 9
V Analysis of 'Value Added' System & Process Steps - Inspection Pharmaceuticals (21 CFR Part 210, 21 CFR Part 211 and related Regulations) 2
P Which ISO 13485 clause(es) are applicable for Value Proposition Creation ISO 13485:2016 - Medical Device Quality Management Systems 1
R The Value and Effectiveness of In Process Inspection Quality Manager and Management Related Issues 17
D Value-Added Analysis - Staff (Employee) Satisfaction Quality Tools, Improvement and Analysis 11
T ISO Auditor Training - What online training is actually value added? ISO 9000, ISO 9001, and ISO 9004 Quality Management Systems Standards 13
M Specific Capability case - Target Value is same as the Lower Limit Capability, Accuracy and Stability - Processes, Machines, etc. 9
S GR&R for an "R" value instrument installed on my 10K Horizontal Tester Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5
S Value Stream Mapping for a Product Family Lean in Manufacturing and Service Industries 5
WCHorn Are Inspection Operations Value Added? Lean in Manufacturing and Service Industries 50

Similar threads

Top Bottom