iSixSigma

Marc Richarsdon

Forum Replies Created

Forum Replies Created

Viewing 12 posts - 1 through 12 (of 12 total)
  • Author
    Posts
  • #81059

    Marc Richarsdon
    Participant

    Robert,
    Try using binary logistic regression in Minitab. Binary logistic regression is a method used to determine how well a predictor variable predicts a binary response. For our purposes, we will define a binary response as the result of a test for which there are only two possible outcomes: in your case, pass or fail.
    By the way, why isn’t your MBB able to help you with your question?
    Marc Richardson
    Sr. Q.A. Engineer

    0
    #81023

    Marc Richarsdon
    Participant

    Thom,
    Thanks so much for the summary. Nothing like using using the tools to better understand and improve the process, in this case, the six sigma process itself. This is an example of why this website, and this forum in particular is so valuable. I only know of one other forum that has this much traffic and its focus is on ISO 9000.
    Marc Richardson
    Sr. Q.A. Eng.

    0
    #80006

    Marc Richarsdon
    Participant

    We test this seal on a tensile testing machine. For this we cut out 3 samples per seal. We started sampling (3 bags per week) because we want to intercept a possible decline in machine performance. Such a decline will manifest itself in lower seal strength. However we know that the bag material shows variation which leads to variation in seal strength. Some people here want to take corrective actions when 1 measurement falls just below spec. In my opinion (based on technical knowledge of materials and machine and partly based on gut feeling) I say things are still ok.
    I have encountered this type of problem many times. First, is this a minimum strength specification? Usually there is no upper tolerance with a characteristic like this. If this is the case, can the process average be shifted up?
    It is really difficult to get people to understand that adjusting a process that is statistically stable because it produces parts that are out of specification actually increases the variation of the process and the product. The funnel experiment shows this very well. You may end up producing more parts out of spec than you would have if you had left the process alone.
    This type of problem usually requires an engineering approach because continually adjusting the process is not the answer. You will probably need to use some problem solving tools like stratifying the data, preparing concentration diagrams and cause & effect diagrams. This will help you to determine the root cause or causes of why the process produces parts out of tolerance. Then you can develop and implement a permanent corrective action.
     
    Maybe I can prove my point with some statistical tools. I know however that I’m not a specialist in this area so I’m being very careful. After all: garbage in = garbage out.
    Well said. It is the wisest among us who recognize the limits of our knowledge and then act to educate ourselves.
    Marc RichardsonSr. Q.A. Eng.

    0
    #75642

    Marc Richarsdon
    Participant

    And those drivers were…
    Thank You,
    Marc Richardson
    Sr. Q.A. Engineer

    0
    #72940

    Marc Richarsdon
    Participant

    OK. I see what happened. You know someone named Mark (with a k) Richardson and mistook me for him. No harm done. I’m just glad we got it straightened out.
    Kelly, looks like you’re right about the 5 W’s/2 H’s. You looked at it and saw one thing, I looked at it and saw another. In the end, we all benefit.
    Thank You,
    Marc Richardson
    Sr. Quality Assurance Engineer
    Kelly, looks like you’re right about the 5 W’s/2 H’s. You looked at it and saw one thing, I looked at it and saw another. In the end, we all benefit.Thank You,Marc RichardsonSr. Quality Assurance Engineer

    0
    #71647

    Marc Richarsdon
    Participant

    Read Juran’s Quality Handbook. In the 4th edition the section on Quality Costs is at pages 4.1 to 4.30. It breaks COPQ down into its standard components:
    Internal Failure Costs
    External Failure Costs
    Appraisal Costs
    Prevention Costs
    If you don’t own a copy (you should), try your local library.
    Marc Richardson
    Sr. Quality Assurance Engineer

    0
    #68870

    Marc Richarsdon
    Participant

    Dear Forum Members,
    Six Sigma Flow Chart Status Report:
    I have emailed the SIPOC for the Define phase to the contributors for review and comment. I am still soliciting contributions for this project. Please send them to the email address below.
    Thanks,
    Marc Richardson
    Sr. Quality Assurance Engineer
    [email protected]

    0
    #67766

    Marc Richarsdon
    Participant

    I am not currently a certified BB (I am told that the climate is not politically correct at this time and even if it was, there’s no money at this time) but I have been using these tools (project management, statistical methods, financial metrics) for many years. For what it’s worth, here are some observations:
    Management buy-in
    Typically, they’ve already spent a lot of money for training and they have a vested interest in seeing results. Have the champion(s) start a monthly SixSigma steering committee. It should be composed of members of senior management. It should be a time here you report on the progress of current projects. It should also be a place where you present and justify the selection of new projects.
    Hopefully as a BB, you are committed to this work full time. Hopefully you are not a part of the QA department. Hopefully management is far-sighted enough to raise this endeavor off the horizon so that everyone in the company understands its importance.
    Financial accountability
    Make sure that the financial officers of the company are on this committee. You need them to set up the collection of cost savings numbers as they are being generated, not as an afterthought.
    Project management
    Weekly round table meetings where everyone comes to report on the progress or lack thereof of their part of the project is a very powerful way to get people to meet their commitments. No one likes to come to a meeting of their peers and say they didn’t get their part of the job done. This assumes that you have previously identified the stakeholders and secured from them the necessary resources.
    Finally, you will just have to get out there and sell hard and then, most difficult of all, deliver.
    Marc Richardson,
    Sr. Q.A. Engineer

    0
    #67284

    Marc Richarsdon
    Participant

    I would like to put a finer point on what Grant wrote. He said “This means if did this 20 times, I would be wrong 1 time.” In actuality, a 5% confidence level means that if you employ this sampling plan 20 times, you just don’t know whether you are right or not one of the times you use it. In other words, it’s not that you will be wrong, it’s that you’re uncertain. Also, keep in mind that you can’t know when that one time is. It could be the first or the last of the 20 samples or anywhere in between.

    Marc Richardson,
    Sr. Q.A. Engineer

    0
    #67259

    Marc Richarsdon
    Participant

    The Automotive Industry Action Group (AIAG) has an FMEA manual. It is based on Ford’s FMEA methods and is the standard for the Automotive Industry. That being said, I find it a little weak on the way they have you estimate the occurence ranking. I have tried to standardize it a bit more by considering the type of inspection (attribute, sampling plan, variable, etc.)

    Marc Richardson
    Sr. Q.A. Engineer

    0
    #66525

    Marc Richarsdon
    Participant

    Hi Jon,

    Perhaps you could be more specific in describing the process for which you are trying to quantify the costs of poor processing.
    Generally speaking, so-called “quality” costs are grouped under to main categories: internal failure cost and external failure costs. ASQ has a number of publications on this subject.

    Marc Richardson
    Sr. Q.A. Engineer

    All opportunities can be realized through sustained analysis.

    0
    #66325

    Marc Richarsdon
    Participant

    Personally, I favor some type of control chart. It gives you a clearer picture of the process central tendency and variation over time.

    0
Viewing 12 posts - 1 through 12 (of 12 total)