iSixSigma

Typical business problem

Six Sigma – iSixSigma Forums Old Forums General Typical business problem

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
    Posts
  • #39913

    Pankaj Gupta
    Participant

    I want  some feedback on a typically problem which i face while working on the data related to banking industry.
     
    The mean time to process a case has been reduced from 1.11 days to 0.15 days
    The standard deviation  in the data has been reduced from 2.5 to 0.50
    The upper specification limit given by the champion of the project team  is 1 day and the lower specification limit has been assumed as zero by the project team.
    Both  the mean time taken and process varition has reduced significantly in the project. However,  when i put the values of mean and standrad deviation in the sigma template  the sigma level shows the following
    Mean         Standard Deviation      LSL              USL   Sigma
    1.11                2.5                           0                   1         1.5
    0.15                 0.5                          0                    1         1.8
    However, if i don’t put the  lower specification value as Zero the Sigma value shoots up to 3.2.
    Since both the mean and the variation has been reduced (standrad deviation reduced by 500% I feel that while calculating the sigma I should not put the LSL as zero in the sigma calculator  since with the LSL as zero there is no significant improvement in the sigma level despite significant reduction in process variation.
    Please suggest.
     

    0
    #122587

    Stephan
    Member

    You can put the 0 days LSL as boundary limit due to the fact that you will not be able to go lower then zero.

    0
    #122674

    Chaturvedi
    Participant

    Yes i can put 0 as LSL . However, how do i explain that there is  only a marginal increase in sigma level wherease the variation in the process has decreased by 500%.  The team will be highly demotivated since they have made significant chnages in the process which has helped them to reduce the mean and the standrad variation.

    0
    #122923

    Stephan
    Member

    I think that the calculation without setting LSL as boundary limits shows you potential out of specification for the LSL, which in fact is not possible. Setting the LSL as boundary has the same effect like eliminating the LSL. The capability calculation is then only towards the upper specification.

    0
Viewing 4 posts - 1 through 4 (of 4 total)

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