iSixSigma

Distribution for time.

Six Sigma – iSixSigma › Forums › Old Forums › General › Distribution for time.

Viewing 5 posts - 1 through 5 (of 5 total)
  • Author
    Posts
  • January 18, 2007 at 12:49 pm #45866

    Peter Örtlund
    ★ 10 Years ★
    Participant

    Hello everyone.
     
    Does anyone have a guideline or at least an opinion what distribution is the most appropriate for the variable “time”? (Foremost thinking about lead-time)

    0
    January 18, 2007 at 6:54 pm #150750

    LBJ
    ★ 10 Years ★
    Participant

    Peter,
    As a general rule time studies are not normally distributed.  If you are familiar with Minitab you can do a best fit test.  Many times, at least in my experience, my time data (repair times) does not fit a set distrbution, so I have to transform my data.  Doing this in Minitab. 
    So to answer your question time data does not fit a specified data distribution.  You simply have to find the best distribution match.
     
     

    0
    January 18, 2007 at 7:51 pm #150756

    BTDT
    ★ 10 Years ★
    Participant

    Peter:Cycle time and time-between occurances tend to follow well understood distributions. Look into Weibull and exponential respectively.Cheers, BTDT

    0
    January 18, 2007 at 8:28 pm #150761

    BritW
    ★ 10 Years ★
    Participant

    Weibull is most likely the distribution  for time.

    0
    January 18, 2007 at 8:43 pm #150762

    Theo
    ★ 10 Years ★
    Member

    Time based processes are usually strongly skewed and commonly bimodal.
    Attempts to fit distributions is one of six sigma’s many fallacies.  There is no need to attempt to fit distributions to such data, in a process improvement context. 
    Learn to understand what the data in the histogram is telling you.
    You can find a useful exercise here: 
     http://www.q-skills.com/nm/nm.htm

    0
  • Author
    Posts
Viewing 5 posts - 1 through 5 (of 5 total)

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