Jen

Uhlan,
Keep in mind that I&MR charts are for homogenous data such as sampling from a waste water influent tank, paint vat, gases etc., meaning if you were to take five samples from something like this there probably wouldn’t be much difference in the range and it would be very similar to having taken just one sample.  However, taking samples in d…[Read more]

Scott,
The process of how your collegue is making variable data is not wrong.  He can even look at the capability as long as he realizes that he needs to look at capability by Operation and decide what percentage (since that is what he is analyzing) the upper and lower spec limits.  If the data is not normal then that needs to be accounted for e…[Read more]

Neo,
I get an undeliverable message when I send to the address you provided me with.  Do you have another?
 
Jen

Paul,
I tried sending it to the email you gave me and I am getting an undeliverable message.
 
jen

Joe,
Think of power in this manner.  If there is a distribution of innocent people that get pulled into a court of law charged with a crime they did not commit then the alpha risk is the portion of that distribution of people that have bad lawyers, planted evidence and a corrupt judge.  The power comes from another distribution that consists of r…[Read more]

Annon,
Yes.  Basically if your lack of fit shows as significant you would want to introduce more data.  You could add additional trials to your original design.  These trials may be centerpoints or going through Response Surface Methodology where you would begin looking at more of a surface as the model you are trying to fit.
 

Annon,
Lack of fit is the difference between the approximation model and the truth.  Basically it describes the bias that you have between your model and the true data.  You can include special runs in your DOE (eg center points) to help describe the fit.  If your DOE maximizes the design efficiency then there will be no lack of fit.
The lack of…[Read more]

JAL,
I set the BB/GB targets as follows:
Maintain acceptable housekeeping of designated work area. Conform to all safety training and personal protection equipment regulations. Work toward improving safety in all facets and encourage others to do the same.
 
* Deliver ($1m) in closed projects. This will be accomplished through a combination…[Read more]

K7,
I have found that communication is key to solving many of my BB projects.  If I am making a process map I go down to the floor and speak with each of the operators about what I am doing and why and I get honest feedback on their processes (including some hidden factory).  When I create data sheets I involve the person that will be taking t…[Read more]

Felipe,
The chart shows you that at the start of your sample size there is greater variation in the prediction of what the true percent defective is.  As your data collection grows you should see the chart level out to a fairly steady number and this tells you that over a larger sample size you are seeing (predicting) a true percentage…[Read more]

mdella,
My Steering Committee has the following monthly agenda:

Assessment of Performance–overview of where all projects are at (# of projects, timing, cost)
Return on Investment Evaluation–what is the current average percent improvement of projects and current “Days to Close”
Stakeholder Assessment and Engagement–review percentage of…[Read more]

Rainman,
A good reference book that I use is Implementing Six Sigma by Forrest W. Breyfogle III.  It is a great reference book.  You are correct, for small sample sizes n<=9 (typically around n = 4 to 6) you would want to use the R value and estimate the standard deviation as Rbar/d2.
For larger subgroups n>10 the above method is less e…[Read more]

REL,
Keep in mind what I put in my previous posting will have you reanalyze the data collected as a 2k with centerpoints, you will not have a general full factorial anymore.

REL,
Your DOE design is saturated, you take up all your degrees of freedom with the factors and leave none for the error factor in the ANOVA.  You can do a couple of things.  First, if you have the resources you can run the experiment again.  You will then have a replicate to provide some information for the error variable.  Or if any of your set…[Read more]

Robin – Unfortunately project budget and time constraints kept me from exploring this any further last fall.
Jen

sorry matey, Six Sigma in freight forwarding, sounds interesting… lemme check if I can find something ..

Thanks, Vinny.  I appreciate your reply regarding the meaning of  ‘plc’. As always, I don’t know what I would do without people of your calibre.
 
Thanks again.

Hello, Steve.  Thanks very much for the answer to ‘plc’.  You people are really great!  Whenver I have needed some technical information, you have always been there to assist.
Thanks for your help.
 

Thanks, Stan.  That was a quick response to my query.  We appreciate it!

Matt,
The biostats textbook I used in grad school at Johns Hopkins was:  
Bernard Rosner. Fundamentals of Biostatistics 2000, Duxbury Press, Pacific Grove, CA
Its a very comprehensive text that’s easy to understand, with lots of examples and problems.
Jen