iSixSigma

Thom

Forum Replies Created

Forum Replies Created

Viewing 11 posts - 1 through 11 (of 11 total)
  • Author
    Posts
  • #57511

    Thom
    Member

    Thank you very much Adam, and now I try to follow your suggestionThomas

    0
    #167588

    Thom
    Member

    Hi all,
    I’m a student and I start with my thesis on “leanSixSigma first then digitize”, can you help me? Could you send to me some papers, .pdf or [email protected]

    0
    #83482

    Thom
    Member

    If you have any questions while using Minitab, a really useful tool is the StatGuide.  With the cursor positioned in the Minitab output (graph or Session Window), click on the icon that is on the toolbar.  Should be just to the right of the question mark icon.  The icon looks like 3 stacked books, with the first book having a cap sigma.
    In this case, it will tell you that the Kappa statistic is a measure of agreement.  Minitab will show a Kappa statistic as well as a p-value.  The hypotheses for the p-value:
    H0: Agreement between appraiser ratings and the standard is due to chance
    H1: Agreement between appraiser ratings and the standard is not due to chance.
    For the kappa statistic, if Kappa = 1, then you have ‘perfect’ agreement, and if = 0, agreement is the same as you would expect due to chance. For Kappa 0.9, the measurement system is great!
    Your Kappa of 0.95 indicates a great measurement system.

    0
    #70503

    Thom
    Member

    Books that I have found useful for Six Sigma:
    Implementing Six Sigma, Breyfogle: good for the tools within the Six Sigma methodology.  Not so good for the infrastructure.  Thus, great reference for Black Belts, not so good for the Champions/Senior Managers
    The Six Sigma Way, Pande: good for infrastructure and simple summaries of the tools.  Good for Champions/Senior Managers and Green Belts.  Not so good for Black Belts in terms of tools — again, just a top level discussion in most cases
    The Six Sigma Revolution, Eckes: great for infrastructure
    When I refer to infrastructure, this means how the program is set up within the organization.  Key personnel, the mission of the program, culture (EXTREMELY LARGE CONSIDERATION)… in essence, your infrastructure and how Six Sigma is positioned within the organization will help deter that killer of all programs: management support.
    Other interesting books: Managing Six Sigma, Breyfogle and Making Six Sigma Last, Eckes.
    Since organization measurement is a huge consideration, it might be interesting to balance the pure Six Sigma literature with Kaplan and Norton’s The Balanced Scorecard.

    0
    #70497

    Thom
    Member

    Howdy TomF,
    Great reply!  Nice illustration of practical versus statistical significance
    For the Lotto example, the practical significance is readily apparent: if you use the exact distribution (hypergeometric), you will find that there is a 1 in 25,827,165 chance of winning the lottery.
    If you used the approximation (binomial), you will find a 1 in 531,441 chance of winning the lottery. 
    Nice illustration of potentially misleading results for an approximation that pushes the rule of thumb… 
    If interested, I can shoot you a nice summary about how you turn that combinatric mess associated with the hypergeometric into a binomial.
     

    0
    #70490

    Thom
    Member

    Hi Dave Strouse,
    Wow!  A voice from the not so distant past…
    I have a nice illustration for the 10% rule of thumb (sample size is less than 10% of the lot size) that I use when I teach this stuff…
    Calculate the probability of winning the Texas Lottery using the hypergeometric and then calculate using the binomial.  The Texas Lotto has 54 possible numbers, and you win by matching 6 out of 6.
    If you use Excel, type in =hypgeomdist(x,n,D,N) where x=n=D=6, and N=54 to get the exact.  To approximate using the binomial, type in =binomdist(x,n,p, false), where x=n=6, and p=n/N=6/54. 
    As a neat trick, type in =combin(N,n) where N=54 and n=6.  How does this compare with the results from the hypergeometric? 
    Note that the hypergeometric function in Excel only returns the mass function — Pr (X=x).  This makes it a little more difficult to construct OC curves on Excel using the hypergeometric, but not impossible.  Reply to this posting with contact information if you are interested in how to set up OC curves in Excel using the hypergeometric.
    However, Excel lets you calculate both the mass and cumulative density functions for both the binomial and the Poisson distributions (that last little statement on the end of the function).  If you type in true, it will give you the cumulative — Pr (X<=x).  If you type in false, it will give you the mass — Pr (X=x).
    Wow… all this probability stuff.  This is one of the reasons that the ANSI spec (old MIL-STD) is still popular.  But, it is what makes them rather dangerous, as well.

    0
    #70265

    Thom
    Member

    Great point, Trigger.  The slide show just gives you screen shots and bullets (no pun intended with the name Trigger), and it makes it rather difficult to gain any value as a reference.
    One other scary thing about this, particularly for the in-house trainers: you get a lot of variability in the training with different instructors, particularly if they differ from the author of the material. 
    One thing that might help a tad bit: use the Notes Page within Powerpoint to provide further information to support the slide.  This adds more substance to the handouts, and might make the handouts more valuable as a reference.
    In addition to this, they may want to align the slides with some worthwhile professional text, and issue this text for the training.

    0
    #69651

    Thom
    Member

    From what Joe has detailed, it appears that his organization may not be ‘ready’ for a Six Sigma methodology.  The consultants will provide some general prerequisites (not their really their fault — they are delivering to a broad base).  Some capture this as the series of the RIGHTS: the RIGHT Measures, the RIGHT Projects, the RIGHT methodology, and the RIGHT People.  If these RIGHTS are not aligned, your organization will be left with a convoluted program.
    The RIGHT Measures should be tied to the organization’s strategy.  These are the Measures that your executive and senior levels of management get excited about — in a crude sense, this is what their bonus structure is tied to.  I say crude because this bonus structure has the obvious flaw of encouraging sub-optimization.  The Measures should be prime generator (or at least check and balance) for projects.  Six Sigma is a gap closing methodology that provides breakthrough improvement.  Breakthrough CANNOT be achieved if you do not know where you want the business to go (strategy) and measures to assess where you are relative to this direction (this includes baseline performance and goals/targets).
    These gaps should provide you with the RIGHT projects.  BUT, you need to make sure that these are actionable and meaningful gaps.  Do not try and boil the ocean when you are in Iowa…  The trick is to tie these gaps to specific product/process performance.
    The RIGHT Methodology could represent an interesting spin…  for your predetermined outcome dilemma, successful completion may achieve breakthrough.  BUT, the right methodology in this case would be Project Management, not Six Sigma.  Another interesting spin… if you lack some of the RIGHTS, use a methodology that will provide you with them.  For example, if you lack the RIGHT Measures, then consider something like Balanced Scorecards or refine the Strategic Planning and Management process.  Include these methodologies within your Six Sigma program.  Be careful of some of the pet methodologies that are out there, though.  You could have too many and dilute the total efforts.  There are also some extremely left-wing methodologies.
    This ties into the RIGHT People.  Infrastructure is key.  This includes more than just Green Belts and Black Belts.  This includes the entire organization, as well as the specific and traditional Six Sigma personnel.  Make sure you have the roles and responsibilities established for the players.  If you want to get really aggressive, establish skill sets and competencies for each position within the organization.
    Now, with all this said, what can Joe do to handle his 5 dilemmas?  Chat with the other Black Belts.  Even if you are isolated, you still have e-mail, phones…  Ultimately, you folks are the talent pool for future Master Black Belts and Champions. 
    However, that future is based on the success you can achieve.  For the opportunities already assigned, address them to the best of your ability.  SHOW VALUE!  Also, aggressively look for other opportunities (including process definition and metrics).  Ask your MBB what you can do to assist (I am willing to bet that your MBB is really losing sleep in the environment that you described).  Take the initiative and schedule your own reviews with the Champion — get them excited about the opportunity as well as incremental gains.  If they are excited, they will take a more active involvement (rather than interest, which is characterized by the “Six Sigma is important” memorandum).
    I hope that this helps…  Best of Luck to all the Joe’s out there!

    0
    #69081

    Thom
    Member

    It looks like Terry has opened up a discussion that should generate a lot of activity.  I am also very interested in getting some semblance of standardization for the MBB.
    The Six Sigma methodology has been gradually evovling towards becoming a profession.  One of the nice things about professions are that roles and responsibilities are clearly and consistently defined.  We as a profession obviously do not have this for the MBB position.
    One way to approach this is to establish competency models based upon what we want the MBB to do for us.  In essence, what we want the MBB to do represents the Y(s) — the competency model, with defined skillsets and competencies, detail the X’s.
    I think that most would agree that the MBB plays a crucial role in any Six Sigma program — with strong and sufficient MBB staffing, a program becomes independent.  That is, the reliance upon the consultants is reduced.  It also provides another rung in the technical ladder for the Six Sigma profession.  With established competencies in required skill sets, you have a nice professional development tool.

    0
    #68631

    Thom
    Member

    Hi Ken,
    First, I would like to thank you for the reply.  In fact, there should be a blanket thanks issued from the iSixSigma community.
    I am very interested in your Storyboard.  If you can send it to me, that would be great.  My e-mail is [email protected].
    Thanks again!
    Regards,
    Thom

    0
    #68552

    Thom
    Member

    Ken is absolutely correct.  If you used paired comparisons for all possible comparisons, you really hurt yourself for your Type I error rate.  Use ANOVA, but be cognizant of the assumptions.  If these do not pan out, consider the nonparametric alternatives (like Kruskall-Wallace).
    Now, some folks struggle with the results from the ANOVA.  Okay, I have concluded that there is a significant difference between treatment means.  Where are these differences?  To answer this, you then utilize multiple comparisons.  There are quite a few to chose from, and you have to understand what you are actually looking for in relation to your Types I and II errors.  These include Tukey, Bonferonni, Scheffe, Duncan’s Multiple Range Test, Student-Newman-Keuls (SNK).
    BUT, with any test/procedure, know what you are testing for, understand the assumptions associated with the test/procedure, understand what diagnostics you have to make (as well as remedial actions).

    0
Viewing 11 posts - 1 through 11 (of 11 total)