iSixSigma

Root cause in Analyze

Six Sigma – iSixSigma Forums Old Forums General Root cause in Analyze

Viewing 9 posts - 1 through 9 (of 9 total)
  • Author
    Posts
  • #29300

    Opey
    Participant

    I am working on a SS project right now, and what we found was that a measure within our scope is a critical X.  What we felt was that we needed to know what caused this X to vary before we could venture into Improve.  Our process is very long and complex, and after 4 weeks of continued investigating the upstream root causes of this critical X, we aren’t even near explaining 95% of it.  When and how do you pull the plug on extra-scopic Analyze activities so that you can move on the measured X and make your improvement?
    I am also wary of coercing my team to “cut bait” on this investigation, because I want them to be 100% in the game.  If they feel that they are bieng controlled or coerced, then they won’t want to play anymore, or at least not as rigorously.
    Anyone wth similar experiences?  Anyone who felt like it was time to move to Improve, but you were outnumbered?
    I am remembering something I read from Jack Welch (the actual guy).  Something like, “When everyone is looking at the same information, everyone usually comes to the same conclusion.”  This seems apropos, and I may have just answered my own question, but I’ll post anyway in case anyone has more guidance.
    Opey

    0
    #74647

    Opey
    Participant

    Bump….

    0
    #74649

    RR Kunes
    Member

    I am interested in what process you are following? Critical X’s are part ofthe Shainin methods..
    In a DMAIC process you let the data guide you. Have you run a DOE (Design of Experiments) to narrow your search? What form of data collection plan have you utilized to usurp the variation and Noise in the process?
    From the wording of your question I’m not sure you are really searching for help or just venting. Let me know if it is actually for help.
     

    0
    #74660

    Mike Carnell
    Participant

    Opey,
    These things do get bogged down from time to time. I have even had a team that there were a couple factions inside that hated each other so bad we disbanded the team.
    You have to play the hand you are dealt. If you rush them to much they won’t be there for you in control when you really need them. One way to get them moving is to do some of the data gathering and analysis yourself. I fyou have light duty people you can get your hands on use them to collect data and run the analysis before you show anyone else. A lot of times if you are moving faster than the crowd the crowd will speed up.
    The other thing is have the process owner stop into a team meeting to get updated and let them ask why it is moving slowly. Do the good cop – bad cop thing.

    0
    #74661

    Mike Carnell
    Participant

    RR,
    There is a basic SS problem solving formula Y = (f)x or Y = (f) x1 + x2 + x3 ….. Not all x’s are equally weighted. The ones that are more influential are critical x’s. Nothing to do with Shanin.

    0
    #74668

    Chris Tinney
    Participant

    Opey,

    Take a real world problem
    Convert it into a statistical problem
    Analyze and solve the statistical problem
    Translate it back into a real world solution
    If you don’t think that you’ve solved the statistical problem in the Analyze phase, how are  you going to implement a valuable real world solution? I don’t think that it will work.
    Your thoughts?
    Chris
     

    0
    #176090

    Perera
    Member

    nothing

    0
    #176096

    annon
    Participant

    If you have gone through ANALYZE, have you not already identified the magnitude and direction of the effects that your causal inputs have on your project Y?  It sounds as if you analysis might be less than complete….
    For example, even if you have a potential KPIV that you can’t measure / control, can you not identify the usefulness of the rest of the model (ie regression model using Rsq, S, Mallows, etc) or block on the uncontrollable factor and run a simple DOE to determine its effect?  If the Rsq explains a significant portion of your variability or the blocking factor proves insignificant, you have your answer….Just my 2 cents.

    0
    #176098

    Szentannai
    Member

    It’s a six years old post gentlemen. I doubt the guy sill needs the advice :)
    Regards
    Sandor

    0
Viewing 9 posts - 1 through 9 (of 9 total)

The forum ‘General’ is closed to new topics and replies.