Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
  • #39352


    I’m confusing about the equation of Zlt = Zst -1.5. How can we get this equation ? 
    For example, we all know that Zst = (SL – Xst)/ást
    And in the long term, Mean (X) shift 1.5ást
    So, Zlt = SL/ást  – (Xst + 1.5ást)/ást
           Zlt = (SL/ást  – Xst/ást) – 1.5ást/ást
    So, Zlt = (SL – Xlt)/ált



    Reigle, where are you when there is a sucker for the taking?


    Reigle Stewart

    To Wuth:
    The following exert is quoted from the “Ask Dr. Harry” section of this website:
    The capability of a process has two distinct but interrelated dimensions. First, there is “short-term capability,” or simply Second, we have the dimension “long-term capability,” or just Finally, we note the contrast Z.shift = – By rearrangement, we assuredly recognize that = + Z.shift and = – Z.shift. So as to better understand the quantity Z.shift, we must consider some of the underlying mathematics.The short-term (instantaneous) form of Z is given as = |SL – T| /, where SL is the specification limit, T is the nominal specification and is the short-term standard deviation. The short-term standard deviation would be computed as = sqrt[SS.w / g(n – 1)], where SS.w is the sums-of-squares due to variation occurring within subgroups, g is the number of subgroups, and n is the number of observations within a subgroup.
    It should be fairly apparent that assesses the ability of a process to repeat (or otherwise replicate) any given performance condition, at any arbitrary moment in time. Owing to the merits of a rational sampling strategy and given that SS.w captures only momentary influences of a transient and random nature, we are compelled to recognize that is a measure of “instantaneous reproducibility.” In other words, the sampling strategy must be designed such that does not capture or otherwise reflect temporal influences (time related sources of error). The metric must echo only pure error (random influences).
    Now considering, we understand that this metric is intended to expose how well the process can replicate a given performance condition over many cycles of the process. In its purest form, is intended to capture and “pool” all of the observed instantaneous effects as well as the longitudinal influences. Thus, we compute = |SL – M| /, where SL is the specification limit, M is the mean (average) and is the long-term standard deviation. The long-term standard deviation is given as = sqrt[SS.t / (ng – 1)], where SS.t is the total sums-of-squares. In this context, SS.t captures two sources of variation – errors that occur within subgroups (SS.w) as well as those that are created between subgroups (SS.b). Given the absence of covariance, we are able to compute the quantity SS.t = SS.b + SS.w.
    In this context, we see that provides a global sense of capability, not just a “slice in time” snapshot. Consequently, we recognize that is time-sensitive, whereas is relatively independent of time. Based on this discussion, we can now better appreciate the contrast – This type of contrast poignantly underscores the extent to which time-related influences are able to unfavorably bias the instantaneous reproducibility of the process. Thus, we compute Z.shift = – as a variable quantity that corrects, adjusts, or otherwise compensates the process capability for the influence of longitudinal effects.
    If the contrast is related only to a comparison of short- and long-term random effects, the value of Z.shift can be theoretically established. For the common case ng = 30 and a type I decision error probability of .005, the equivalent mean shift will be approximately If the contrast also accounts for the occurrence of nonrandom effects, the equivalent mean shift cannot be theoretically established – it can only be empirically estimated or judgmentally asserted.
    I hope this helps you.
    Reigle Stewart



    Any shift would be detectable long before 1.5s on a Shewhart Chart, and even more quickly on a Cusum chart?
    Most process engineers know ‘process performance’ is calculated on the basis of 30 subgroups of size (3 to 5) – not 30 individual measurements!

Viewing 4 posts - 1 through 4 (of 4 total)

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