TableCurve finds that a Lorentzian peak is a slightly better fit than a Gaussian peak, but I agree with Mike that your starting data, at first glance and with no context, looks more like a peak than a process that is in a state of statistical control. This is an easier measure of variation to compute than the standard deviation, though with modern computer hardware and software that’s not an important consideration. I added a column to my table to calculate the Moving Range, which is simply the absolute value of the difference between the current value and the previous value. Understanding Variation: The Key to Managing Chaos In this example, I relied on techniques from a small, 136-page book called Understanding Variation. This is an opportunity to illustrate another set of run charts. I wrote about Control charts in Introducing Control Charts (Run Charts). I thought a moment and realized that with many weeks of repeated data, what the user needed was an approach based on Statistical Process Control. I replied to the user with this suggestion, and he said that wouldn’t work, because the data would have to be fitted with many line segments, because the data he gave me was only part of a much larger sequence of values.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |