Mike Carnell


  • For starters you will need to track the work flow of each department with respect to needed input from other departments. As described you are making the assumption all departments function independently of one another – that is, any work done in any department does not require anything from departments external to it in order to complete a…[Read more]

  • The simplest thing to do would be to take your data and run a one sample t-test against a target of 2 and see if they are significantly different. The t-test is robust with respect to non-normality so that shouldn’t be a problem (if you need a reference – The Design and Analysis of Industrial Experiments – Davies – 2nd Edition pp.51-56).

    If…[Read more]

  • Hi Sue,
    Glad you are interested in joining the Six Sigma community. Feel free to send me an email and contact info to discuss how I might be able to help you. You can also check me out on this site as well as LinkedIn.

    Dr. Ken Feldman
    [email protected] 1 month, 1 week ago

  • Nelson’s rules cover a multitude of patterns in a control chart and you can use any of them with the data set I provided.
    For the 15 point rule your answer will be, “I didn’t see that pattern in the existing data.” The follow up question would be – did I see a violation of any of the other rules?

    The provided data set will allow you to run…[Read more]

  • The attached data set was part of a discussion thread back in June 2018. The poster was asking about changes in the batching of color addition and he/she provided this production data. You could take this data and use it for your problem. There are 10 batches of material and the color count is a count of number of times a color additive was…[Read more]

  • You use calculated +3/-3 for control limits and don’t change them without good reason. But I can surmise this isn’t your real problem. As all of us have experienced, customers don’t give a damn about statistical control limits. We want to get help as fast as possible and the longer it takes the less happy we are. We don’t give a damn if the call…[Read more]

  • Wanting to beef up your skills to become more valuable is the right attitude. You chose two very good resources. Will studying them be sufficient to pass the GB exam? If you have a good basic understanding of statistics and business processes, it might be. You might consider a practice exam which you can get from several sources, or take the…[Read more]

  • I would recommend you tell us what you think and why. This will assure everyone that you have taken some time to think about the problem and probably guarantee a response to your question. If you don’t do this then all you are asking is for someone to do your homework for you. 3 months, 3 weeks ago

  • The expression is the equation for expressing the 95% confidence limit around the mean (See for example Statistical Methods 7th Edition – Snedecor and Cochran – pp51-53) . If you have an infinite sample size the 2 will become 1.96 but, unless you happen to know the exact sample size for the mean (which you don’t) the usual practice, for an…[Read more]

  • One control chart for an entire call center isn’t reasonable. You are making no allowances for differences in call type, call difficulty, operator experience, staffing differences (time of day, weekends, skill sets, etc.) and so on.

    If you want to lump everything together and ignore all of the above you could do this just to see what you…[Read more]

  • Feel free to calculate per product but you can calculate per shift just fine. 6 months ago

  • Check out something referred to as the 1.5 sigma shift. There has been much debate on this site as to the source and validity of the concept. It will explain why the traditional 3.4 defects per million definition of 6 sigma shows up in the Z table as 4.5 sigma and not 6. 6 months, 1 week ago

  • Congratulations ce_seek. You’re welcome. I’m glad I was able to be of some assistance. 7 months ago

  • As an analogy….once you reach your desired weight after a diet, do you stop weighing yourself? No. You keep monitoring your weight to be sure it doesn’t change. The same would be true if you reach your desired blood pressure because you are taking drugs to help you. You would still periodically take your blood pressure to make sure nothing…[Read more]

  • If you have zero defects, then you wouldn’t need it. It would be hard to imagine zero defects over a long period of time if you show a lack of control for the short amount of time captured in your chart.

    If you had a Cpk and Ppk of 2+, then go elsewhere first.

    Please be aware that specification limits aren’t used for control chart…[Read more]

  • the takt time is different for each process. reference the formula you have in mind. 7 months, 3 weeks ago

  • No, you do not need a minimum of 30 samples – Gossett put that bit of nonsense to rest back around 1908 or so. Other than the fact that the basic Cpk calculations require data normality there is no connection between 30 samples and normality. Take what you have and press on with the calculation. If you are really concerned about the structure of…[Read more]

  • You can do a capability analysis on attribute data. Check Chapter 9 – Measuring Capability with Attribute Data in the book Measuring Process Capability by Bothe – you can probably get the book through inter-library loan. 9 months, 2 weeks ago

  • I’m not trying to be rude or offensive but the short answer to your question is – start over.

    1. You will need to provide more information concerning the QA score – what is it and how is it quantified?
    a. Is this some kind of personal assessment by yourself – i.e. a 1-10 Likert score based on perception or is it something that is…[Read more]

  • I can’t imagine doing SPC on amount in and amount out if you are looking at quality as your pain point. Knowing nothing else of your process, why not look at quality % with a run chart. If you’re going to do SPC, I bet you’d have too many things to investigate if quality goes out of control. 10 months ago

  • Load More