OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests :B Vs C

Good reference :World Class Quality Keki R. Bhote AMACOMISBN: 0-8144-5053-9; 1991 Chapter 11 describes this B Vs C with examples It is also called the six pack test because it just requires 6 samples as 3 of B and 3 of C. B = Better or new process C = Current or old process

1/1/03

Class 2 Non-Normal Data Steve Brainerd

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests :B Vs C

B Vs C test BASIC IDEA: Very simple and powerful test. It is based upon a ranking of the 6 samples taken. Basically there are 20 combinations of 6 samples taken 3 at a time. There is a 1 in 20 (5%) chance that all the Bs would be ranked higher than the Cs due to random chance. If all the Bs are higher than the Cs, then we can state with 95% confidence that we improved the process!
1/1/03 Class 2 Non-Normal Data Steve Brainerd 2

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests : :Shainin B Vs C test also called 6 pack test

Shainins Six Pack Test Many current weathering studies use parametric statistical tools to analyze results. Researchers should not overlook non-parametric tools for weathering data analysis. Non-parametric analysis can be especially useful in weathering studies involving appearance issues and visual evaluations for acceptability ranking. Also, often nonparametric analysis does not require normally distributed data to be effective. Dorian Shainin has developed a system of unique techniques for process analysis in manufacturing environments. Shainin developed the concept known as "The Red X" source of variations in manufacturing processes.

1/1/03

Class 2 Non-Normal Data Steve Brainerd

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests : :Shainin B Vs C test also called 6 pack test Shainins Six Pack Test Shainins logical approaches to production processes may also represent valuable tools for investigating weathering processes. One such tool includes Shainins "6 pack test." Results are rank ordered. The ranking is then associated with input variables. The probabilities associated with a specific order are then evaluated.

1/1/03

Class 2 Non-Normal Data Steve Brainerd

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests : :Shainin B Vs C test also called 6 pack test Shainins Six Pack Test For example, two different lots of automotive paint were obtained from a single supplier with a single formulation. The research question was to see if lot to lot differences could result in different weathering characteristics. Three randomly selected specimens from each lot were exposed side by side, backed in Florida at 5 South for six months. After weathering, the specimens were measured for color. The b* values were ranked. The ranking and corresponding batch numbers associated with each b* values are as follows:

1/1/03

Class 2 Non-Normal Data Steve Brainerd

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests : :Shainin B Vs C test also called 6 pack test

R a n k O r d e r o f S ix S p e c im e n s 1 2 3 4 5 6 b * v a lu e a f t e r 6 m o s ., F lo r id a , b a c k e d , 5 0 .2 9 0 .2 8 0 .1 9 - 0 .0 8 - 0 .1 8 - 0 .1 9 B a tc h N u m b er s

881 "W " 881 "W " 881 "W " 921 "T" 921 "T" 921 "T"

1/1/03

Class 2 Non-Normal Data Steve Brainerd

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd

Non- Parametric tests : :Shainin B Vs C test also called 6 pack test

There are 20 different equally likely rank orders for these 6 specimens. Similarly there is only a one in twenty chance that the three "W" specimens would all rank above the "T" specimens. The likelihood of this particular order from chance alone is 1/20 or 0.05. This handy little tool is an effective way to identify vital variations with out requiring normality or distribution tables. Readers are highly encouraged to seek out additional Shainin techniques for weathering processes, as well as, manufacturing process solutions.

1/1/03

Class 2 Non-Normal Data Steve Brainerd