iSixSigma

Utah123

Activity

  • I would identify your customer requirements as they apply to the scope of the call center.  Use a basic VOC study to include who you are targeting, what you need to know about their requirments, what information is currently available about said requirements, and what proactive steps are required to fill the gap between the “what you need to…[Read more]

  • Utah123 replied to the topic Transfer Function in the forum General 15 years, 3 months ago

    Thanks Ken.  That helps!

  • No sir, that was great.  As always, I sure appreciate your time.  Thanks again.

  • Gotcha…as a matter of procedure, I would always begin my analysis with a check for stability (run chart or CC), and deal with special cause at that point, before doing anything else.  Once stabilized, I would then look to Shape and deal with the issue of distribution at this point.  Assuming a proper MSA, lack of special cause and spe…[Read more]

  • I was assuming a non-normal Project Y during the initial collection process, but you bring up a good point:  What if running an ANOVA and one or more levels prove non-normal?   I would assume you would move all levels over to the non-parametric test, as it should be robust to normal and non-normal, yes?  Or is there a cause there worth inv…[Read more]

  • You are correct…I am more intersted in the practical understanding of how to interpret and apply and I appreciate your time…..if indeed you treat normal data as non-normal inadvertently or otherwise, will the DMAIC process indicate this error in some way?  For example, in the R-adj once modeled?  Or are you ignorant to the fact until your ch…[Read more]

  • BTDT,
    What a great answer…exactly what I wanted….thanks for taking the time. 

  • Here is my .02….Your project Ys appear to be order accuracy and loading time.  You can choose to look at both or reduce your scope and look at one at a time.  The latter may be a better choice for your first project.  A key point is defining how each is measured:  order accuracy is defined by an external customer, so ensure you are both meas…[Read more]

  • Perhaps a proper DOE might provide you with more pertinent information in a more economical fashion.  It would allow you to test the relationship between multiple independent variables (fiber type, weave density, range, etc) against the vest’s stopping power (dependent variable), which you would want to quantify specifically in a meaningful way (…[Read more]

  • Utah123 replied to the topic Z-value in the forum General 15 years, 5 months ago

    It is confusing….The key point to remember is you are simply trying to determine the current capability of your process.  This requries some metric that will allow you to compare the actual error in your process to the amount of error the customer will allow.  Hence the need for the process standard deviation and customer toler…[Read more]

  • My experience only:  Ask your MBB as to protocol, failing that, refer to Accounting/Finance, as your ROI will often require their sign-off.  BB/MBB time is captured as a cost in some metric for the project, either as an ROI or as a required return during the assessment and selection phase.  This is a policy issue that should be standardized acr…[Read more]

  • Utah123 replied to the topic Streamlining in the forum General 15 years, 5 months ago

    The words LEAN event come to mind….you will need to fully understand the demand and capacity of for each of your transactional work cells. In a very small nutshell:

    Determine each task grouping performed by your team
    Determine the daily demand of these tasks (generally an average, depending on your lead time)
    Determine your current…[Read more]

  • Utah123 replied to the topic Z-value in the forum General 15 years, 5 months ago

    Z Score –  Basically, it tells us how many standard deviations a specific data value is away from the mean.  It can be computed for each data value as follows:  x-x-bar / s
     

    Z score – the number of s the data value falls above (+ Z) or below (-Z) the mean.
    Z scores are highly influenced by outliers, as it is calculated from the mean and s…[Read more]

  • The key point to remember is variation must be looked at within the context of tolerance.  If within control limits and specification limits, your resources are perhaps better spend elsewhere.  If looking at a single factor, I would not consider the magnitude of the variation outside the context of the process capability.
    If looking at mult…[Read more]

  • Utah123 replied to the topic 5S in the forum General 15 years, 6 months ago

    I think the other areas of LEAN may be more applicable…looking at current state and future state VSM while seeking to reduce waste (7W)…gaining speed and accuracy within a transactional enviroment may be better served using these techniques (which includes 5S). 
    Check out “Learning To See”…great book….simple, straight-forward, and b…[Read more]

  • Utah123 replied to the topic Tollgate snafus in the forum General 15 years, 6 months ago

    BTDT,
    Can you elaborate on the MC simulation as it applies to your comment?  Thanks!

  • Utah123 replied to the topic Losing my shorts in the forum General 15 years, 6 months ago

    I was going to be a doctor, but those pesky sciences kept getting in the way….two things:
    1.  For your mathmatical shortcomings:  Probability is your friend…read a book….”Idiot’s Guide to Statisitics” should do the trick
    2.  For reading tells:  “If you can’t spot the sucker at the table, you’re it”….looks like you need to find you a tabl…[Read more]

  • Utah123 replied to the topic Normal Distribution in the forum General 15 years, 6 months ago

    Practically speaking:  A normal distribution allows you to use standardized sigma tools for your inferential analysis.  It tells you the tools taught to you (Hypothesis Testing, Process Capability Ratios, etc) will fit your data set reasonably well.  Practically, that is why you care.  If your data set shows to be other than normally dist…[Read more]

  • I did indeed miss-speak.  Thank you for correcting me.

  • Perhaps I mis-spoke…..
    The central limit theorem states that given a distribution with a mean m and variance s2, the sampling distribution of the mean appraches a normal distribution with a mean and variance/N as N, the sample size, increases
    It was my understanding the CLT (central limit theorm) indicates a data set will move toward…[Read more]

  • Load More