I am interested in the norms for turnover also.
Industry: Meat slicing and cooking (not slaughter, not restaurant)
City Size: Apx. 8,000
What is the source for that type of information, and how do they define turnover?
Shucks, slide rule and French curves are not antiquated … my bamboo Post Versalog slide rule is still in my desk at home, as is my French curve. It was interesting that, even in fun, someone said that they would sell theirs for an exorbitant price. Shucks, I will sell mine for twice that price…
I remember the day when we looked back on t…[Read more]
Questions: Is the frame symetrical about the center? Is the same device/press applying pressure at all four corners? Is the pressure at all corners the same?
My thought is that if the answer to any of the above questions is No, then you do not have 4 Y’s, but rather that you have four relations to figure out, each with a single Y.
Just c…[Read more]
Perhaps my perspective is wrong, but this is my perspective:
When I have a project to work on the issue is studied, and the available information is roughly Y=f(x1,x2, x3, x4, x5,x6) — assuming that one has identified 6 variables at that time.
Some variables that could be manifested will be unknown to the team, variables x7, x8, .…[Read more]
As most of the replies do not seem to have a cohesive answer, try this for a response:
When calculating a process sigma, one needs to consider two things into the calculation:
#1: Since the calculation is based on a finite number of data points, we have sampled the “true” sigma, thus we have obtained an estimate of the sigma, not the sigma…[Read more]
OK, I’m slowly getting a better grasp on the DOE construction, and weighing the time and the number of runs. I did, however come across a book that discusses the degrees of freedom and it seems to dispute that a 1/2 fraction 4×5 DOE with 10 replicates (100 test results) would have 90+ dof as suggested.
In Fitting Equations to Data, Computer…[Read more]
OK on the DOE under discussion.
In general is it correct to say that you picked the half fraction because 2^3/2 = 4, the highest level in the DOE?
Is it correct to say that the number of replicates was picked to be the same as the odd level factor. Is that a general strategy or just a concidence of the DOE considered?
Now it is not general…[Read more]
My response is in two parts:
1. I did a study at one time, where I generated 25 sets of simulations of a normally distributed data set, each consisting of 7,205 data points to yield 1,441 means and ranges (used a sample size of 5) for each of the 25 simulations. I then compared the sampled UCL (based on the ranges) to the standard deviation o…[Read more]
I was told in training classes to just pick the distribution with the lowest AD value, but wondered if that was really so – or if there were dangers out there.
To test that suspicion I used MiniTab to create around 50 data sets, each normally distributed with a mean of 0 and std. dev of 1. Then I had MiniTab compute the AD values when I told it…[Read more]
An alternative explanation for my instructor is that at that time he just did not have time to provide a better reply — I’ll give hime the benefit of the doubt on that.
Aside from that, with your assistance, I was finally able to find the within clarification in the Stat Guide. Thanks to all that helped.
One aspect that is not covered in the stat guide:
I can use CALC to generate 50 normally distributed numbers with std dev of 1 and mean of 0, no challenge there.
Now I select STAT > QUALITY TOOLS > CAPABILITY ANALYSIS > NORMAL and set the USL to 1, the LSL to -1, and the subgroup size to 1. The result is that the StDev(within) does not equal St…[Read more]
Aside from the materials, there are some things that you should consider independent of the materials.
First: Establish your training objectives. I generally establish about 5 or so, but that depends on the length of the teaching session. Make the objectives relate to what you are trying to do, but fairly definitive. Then sha…[Read more]
Thanks for the reply.
Is the manner of fractionalizing correct?
I am expecting interactions, and interactions through ABB or BAA, but unlikely that I will find AABB terms, so that is why I have the levels set where they are. While it is correct that the squared terms may be found with 3 levels, each level of measurement will have some…[Read more]
Last line of cases shoukld read Mod(5,3), not Mod(5,5). Error due to a mismatch between speed of mind and speed of fingers.
I am watching for alias as follows:
For A alias with AB, take level of A minus product of level of A with level of B. For a given fractionization, all of the run values should not have the same value. I.e.
To get a graphic of that, I’d be tempted to use the “Bubble Chart” in Microsoft-Excel. It’s under the standard graphing options, about the tenth option under Chart Wizard. That does no hypothesis testing, but should be a reasonable graphic of the results.
Don’t know about a movie, but the below link may assist your search. Let us know if you find a movie.
- Load More