Paul Keller


  • If process personnel adjust the process to meet specifications, and the process is inherently incapable of meeting the requirements (i.e. Cpk<1), they are tampering with the process, which Deming showed in Out of the Crisis actually increases process variation.

    It’s best to first analyze your processes for statistical control. If not in control,…[Read more]

  • Better version of the charts attached. 11 months, 4 weeks ago

  • Hi Carlos,

    You have a few things going on there. First, you shouldn’t use a Range chart to estimate variation for subgroup sizes >10. In fact, the subgroup standard deviation (i.e. X-bar Sigma chart) is always better. The Range chart was developed in the 1920’s before calculators or computers were prevalent, but better estimates are provided with…[Read more]

  • I don’t see an issue with your company setting a standard for process capability of Cpk=1.33. This is a fairly standard practice, and 1.33 has been the suggested goal for Cpk since the 1980’s as it provides a bit of margin of error in case the process shifts without detection.

    So, your question is how to respond when the process cannot meet that…[Read more]

  • Paul Keller's profile was updated 11 months, 4 weeks ago

  • Paul Keller posted a new activity comment 4 years, 10 months ago

    Despite the tease at the beginning, I’m glad to read the conclusion that pre-control charts are generally not recommended. Yet, there are a couple of issues that should be noted:
    1. You state “The individuals chart is also the most sensitive of the Shewhart charts…”. Actually, the Individuals chart is the LEAST sensitive of Shewhart control cha…[Read more]

  • I write for a living, so its not too much effort, especially since I pasted at least some of the content from my company website. The individual who asked the original question had a very legitimate concern, which had not been properly addressed by other readers. I have a passion for the topic, and like to assist where I can.
    8 years, 4 months ago

  • As I said, the formula for calculating the standard deviation of a set of empirical data is different than the formulas for calculating the standard deviation of a presumed distribution.
    You might investigate some of the peer-reviewed journals on quality engineering, including the Journal of Quality Technology (published by ASQ), Quality…[Read more]

  • Paul Keller changed their profile picture 8 years, 4 months ago

  • Trish: The standard Individual-X chart may work, depending on how large or small your cycle times are. As the process improves towards smaller cycle times, it will become bounded by the smallest possible cycle […] 8 years, 4 months ago

  • Darth,
    The EWMA chart has many uses. Its historic use (for which is was originally developed) was in analysis of serially-correlated data. Its use is not restricted to that, and has many practical uses for independent data as well.
    I am a fan of proper data analysis. (period). I respect the original work of Shewhart, and the many well educated…[Read more]

  • Darth:
    The referenced web page said that distributions may be characterized by several parameters: central tendency, variation (standard deviation or variance), skewness and kurtosis. The link from the standard […] 8 years, 4 months ago

  • Katie: Sorry about that. I was simply trying to provide more information than can easily be typed into this forum. 8 years, 4 months ago

  • Enter the subgroup size as 1 8 years, 4 months ago

  • A properly designed control chart will differentiate between common and special causes of variation. The Box-Whisker chart will not, and you then run the risk of increasing process variation by incorrectly […] 8 years, 4 months ago

  • As others have noted, there are many reasons for non-normality. Yet, you cannot simply take a set of process data and test it for a distribution until you know whether the process is in control. If the process is […] 8 years, 4 months ago