DrSeuss

Allen,
Is sound like you are asking the standard question; “how many data
points do I need to collect?” You need to use a sample size
calculator, like the one on this site. See iSix Sigma tools or
calculator links off the home page. What you are looking for is
something that will require to choose a confidence level for your
expected…[Read more]

Check out the series of articles from this iSixSigma site on what to do if your data is non-normal.  The articles will walk you through each of five options for handling your data, by the way, transformation is the last option.
 
 

Chuck,
I don’t know if you are part of operations, manufacturing engineering or shop floor labor, but inorder to overcome the resistance to change, you need to motivate all to participate in creating a vision of a better process.  Try this out.  You have a mature process with some issues and you would like to make it better.  Your workers know mo…[Read more]

VoteforPedro…….How is Napoleon doing?
First Question:  With a gage where you are measuring deviations in fractions and with a straight edge bothers me somewhat.  Are you looking for a simple GoNogo gage?  If this is the case, just set up your fixture with a max and or min pin or scale and use an attribute R&R to evaluate the gage’s ef…[Read more]

Regina,
Now that I have read your initial question that started this thread.  You are right about the differences between calibration and measurement variation due to R&R.  Think about what you are trying to verify from a practical sense, can your tessa or OGP devices take repeated measures of the same thing within some allowable margin of u…[Read more]

You can also try designing an experiment to validate your measurement system.  Basically you can use hypothesis testing comparing your current measurement performance versus a calibrated standard.  A paired t analysis using the same parts would indicate possible changes over time or usage intervals.  Make sure to include the confidence interval to…[Read more]

Darth,
Yes, we are very much aware of an evil disturbance in the Force.    The princess is well protected and dumb like a fox.  Take care.

Thanks Bob, now I understand what’s going on. 

Hey Folks!  Does it really matter who trained who? 

Gabrielle,
As you have seen from the replies, there are many that people use for process mapping.  One I find that works well is iGrafx’s Process 2005 Flowcharter.  This product has been around for years and has evolved very nicely.  Originally developed as an Apple Mac application, it has been merged with Process Model simulation software in it…[Read more]

Gabrielle,
As mentioned in the other posts, there are many.  One I particularly like is iGrafx’s Flowcharter.  Two reasons this software works for my applications:
1.

Ron,
Here is my experience with Minitab software, back in the dark ages of Minitab 10.5 – 12 eras, a company trainer indicated that running the Normality test on sample sizes less than 25 was not very productive.  Seems that Mini would yield a big p-value and you would assume you have normal data.  It wasn’t until your sample size was as lea…[Read more]

Sally,
Your dilemma is not a new one.  Believe it or not, in many cases the non normal tools are easier to apply than the ones for normal data.  You really need to take a course in non parametric statistics and distributions.  If your schedule is like mine, attending a course that lasts longer than one or two days at the most is almost im…[Read more]

Ray,
Your delimma describes a battle I have many years ago in a former life.  I assume that your machine and touch probe have been calibrated and the table meets all the required flatness standards.  Here is an approach that might apease your leadership and give you what you need.  Look at the part/s involved with your project and catorgorize th…[Read more]

Jack Welch earned both his GB and BB.  Most CEO’s that I have met usually know their businesses and associated processes better than most.  Remember they typically are not detail focused but big picture focused.  They have detail experts to dot the i’s and cross the t’s

Sounds like your company is in trouble and doomed to go out of business.  The whole purpose of Six Sigma methodology is to transform an organization into a data based decision making team.  Hopefully the data analysis skills have been perserved in the control plans of all the successful projects.  At some point, belts should not really be ne…[Read more]

I feel your pain…
If what you are looking for is the spreadsheet version of a pivot table, then in Minitab go to Stat>Tables>CrossTabulation.  This will get you the summaries that you are looking for.  Not quit as elegant as Excel’s pivot table options, but it should be adequate.  Also, in the future, if you want to do something custom or sl…[Read more]

Here is the easy answer to your question, my Minitab instructors told me that you must have a sample size of at least 25 data points for the AD Normality test to have any credibility.  Using that as a rule of thumb, have more than 25 data points.  The other side of this discussion is centered around the strengths of the Anderson Darlington ve…[Read more]

DT, let me try to answer this from a practical experience approach,
I have also asked this question and have never receive a definitive academic answer.  Here is what I have seen from analyzing real process data.  Take a continuous process and produces data that is normally distributed (near normal is also good enough) and collect your data u…[Read more]

Rainman,
The beauty of the DOE is that if you started your analysis with an orthogonal array, namely, an arrangement of factor combinations that was established using typical software, such as, Minitab; then the independence of your factors and interactions is guaranteed.  Basically, each main effect and interaction effect is independent of each…[Read more]