ANOVA for Tailgate Samples

Automotive inspection, TS 16949, IATF 16949

Q: I have a question that is related to comparison studies done on incoming inspections.

My organization has a process for which it receives a “tailgate” sample from a supplier and then compares that data with three samples of the next three shipments to “qualify” them. The reason behind this comparison is to determine if the production process of the vendor has changed significantly from the “tailgate” sample, or if they picked the best of the best for the “tailgate.”

It seems a student’s t-test for comparing two means might be a simple and quick evaluation, but I believe an ANOVA might in order for the various characteristics measured (there are multiple).

Can an expert provide some statistician advice to help me move forward in determining an effective solution?

A: Assuming the data is continuous,  ANOVA (or MANOVA for multiple responses) should be employed. Since the tailgate sample is a control, Dunnett’s multiple comparison test should be used if the p-value from ANOVA is less than 0.05.  If the data is discrete (pass/fail), then comparing the lots would require the use of a chi-square test.

Steven Walfish
Secretary, U.S. TAG to ISO/TC 69
ASQ CQE
Principal Statistician, BD
http://statisticaloutsourcingservices.com/

ISO 17025 Clause 5.4.2 – Selection of Methods

ISO/IEC 17025:2017 General requirements for the competence of testing and calibration laboratoriesQ: We are working with the Mexican Accreditation Entity (EMA) for certification to ISO/IEC 17025:2005 General requirements for the competence of testing and calibration laboratories. Clause 5.4.2 states: The laboratory shall confirm that it can properly operate standard methods before introducing the tests or calibrations.

We are a testing laboratory and work with Method 21 – Determination of Volatile Organic Compound, EPA 40 CFR Ch.1 ( 01/07/04 Edition ) Test: Monitoring of Fugitive Emissions.

The question is: What would be the best way or a way to confirm the method? Or, to put it another way, how can we satisfy the requirements in clause 5.4.2 ?

A: The questioner is referring to clause 5.4.2 from ISO/IEC 17025:2005. An excerpt of this clause is below. Please refer to ISO/IEC 17025:2005 for the full clause.

5.4.2 Selection of methods

“…Methods published in international, regional or national standards shall preferably be used….. Laboratory-developed methods or methods adopted by the laboratory may also be used if they are appropriate for the intended use and if they are validated…. The customer shall be informed as to the method chosen. The laboratory shall confirm that it can properly operate standard methods before introducing the tests or calibrations.…”

Since the questioner is using the published methods, there is no need for validation of the method unless the method is modified.

However, the proficiency of being able to apply the published method needs to be demonstrated. This can be demonstrated by a documented Gage R & R study, Analysis of Variance (ANOVA) or Design of Experiments (DOE) study as appropriate to show proficiency in being able to utilize the test method properly.

The results from these studies may also be used to estimate the uncertainty of measurement for the tests. Reporting uncertainty of measurement with both test and calibration results is a requirement in ISO/IEC 17025:2005. The ILAC P14 document is a good guidance document on reporting uncertainty.

Dilip A Shah
ASQ CQE, CQA, CCT
President, E = mc3 Solutions
Chair, ASQ Measurement Quality Division (2012-2013)
Secretary and Member of the A2LA Board of Directors (2006-2014)
Medina, Ohio
www.emc3solutions.com