Kim Niles

Just brainstorming… I’ve coached a few military oriented Lean Six Sigma projects and always had to chuckle regarding the value saved. Projects that redesign the system so armored tanks wouldn’t go missing… saved $200MM, etc. Perhaps your art could utilize pictures of large pieces of equipment that’s been found in some way… not sure. Good…[Read more]

Kiran:
Good question, I had a statistics teacher answer this question once by telling me that correlation analysis is always through visual interpretation and regression analysis is always mathematical.   I’ve stuck with that definition even though I’m not very comfortable with it.  I hope to read more posts on this string. 
KN  – http:…[Read more]

Nats:
I just want to be clear that “replicates” are defined as repeat experiments whereas “repeat measures” are defined as multiple samples per run.  Perhaps you’re just getting caught up in definitions. 
In this case, you need to measure variation in the “repeat measures” in order to compare variation in the factors.
KN

Nats:
ANOVA is in essence a signal to noise measurement used to provide confidence (variation based) in factor effect (factor means) measurements.  It doesn’t compare variation relative to the factors to that end.  I believe it was Taguchi who outlined using run related signal to noise measurements and or standard deviation / variation as you st…[Read more]

Thomas:
 
Three thoughts, one is to make sure you explain what will become the assumptions you use in your final report so you can later go back if you want and analyze the effects of temperature changes.  For example:
–          One hour is assumed to be sufficient for temperature change stabilization.
–          The split plot approach was c…[Read more]

Neel:
 
Regarding subjectivity, one of the main reasons why Six Sigma works is that it attracts top management.  Top management tends to react to concrete financial figures.  Therefore, it can be argued that Six Sigma should remain somewhat subjective as its success lies in part to its ability to expose subjective costs that always do exist in…[Read more]

Thanks Bill and Robert:
 
Interesting conversation.  One quick thought I have related to problem solving is that benefits are usually obvious so the trick becomes developing a test strategy / test plan that justifies the effort.  Also, remember that the benefits are not always known in advance such as when new discoveries are made or factors su…[Read more]

Dear JAG:
 
One more thing to suggest that I don’t see mentioned in other posts is to prioritize your 10 factors and fix in place as many as seems reasonable to the team before you start your DOEs.  This is assuming your goal is to produce evidence of a stable process for selling that product.   
 
I like to adopt a RPN prioritizing system…[Read more]

Dear Tim: You’ve got some great ideas here and I’d follow them first.  However, after you’ve performed multiple regression analysis and other forms of plotting to highlight what controls your situation, you might want to try to generate a mixture DOE from passive data.   It might be tricky to find representative data but if you are able to do tha…[Read more]

Dear J.K:
 
I like Michaels idea of performing a DOE on the whole process but would suggest you test within acceptable tolerances on production with every run being one entire day’s worth of production.  Your response will simply be the quantity of special rejects for that day.  
 
Since you don’t have a clue as to what causes the spe…[Read more]

Harry:
 
You might want to read this site at http://www.math.toronto.edu/mathnet/questionCorner/geomean.html where you will see how the geometric mean answers the question, “if all the quantities had the same value, what would that value have to be in order to achieve the same product?”.  Since the arithmetic mean answers the question “if all th…[Read more]

Dear John, et al.:
 
This is a very interesting conversation to me as not much is written on the 5 sigma wall and or obtaining very high sigma levels. 
 
Since any process sigma can also be considered to depend upon how close the outer edges of the process distribution (what is) comes to the specs (what should be), achieving high levels of si…[Read more]

Gordo:
Here’s a couple points of advice:
1.      Make sure you watch what happens as possible.  I’ve performed similar experiments thinking those taking the data are well trained only to find out they mixed the samples in the bags.
2.      Throw in one variable that you already have a good feel for as possible.  That way if the results for t…[Read more]

Dear Andy:
 
Since no one has commented I’ll give you my thoughts.  Take them with a grain of salt … :) 
 
Regarding your first sentence, as I understand your question, DOE’s measure these issues as error and or how well the data fit the model depending upon the type of problem.  When the R^2 value is low then your data did not fit the model…[Read more]

Vincent:
Context based questions always peak my interest … .
My answer to your question is “yes” when the context surrounding the sentence supports it and “no” when it doesn’t.  The word “Factor” for example could be referring to a control factor or a response factor … big difference. 
Does that make sense?
KN – http://KimNiles.com

Dear MLT:
Improving anything costs money or other resources and therefore should take place in accordance with need.  There is a spectrum of different types of effort that might be required from individual task levels to full time sequestered team based efforts.  Six Sigma projects are somewhere in between. 
 
Each level of effort has an app…[Read more]