Jump to content
  • 1

Variation Reduction vs Mean Improvement

Variation Reduction implies reducing the standard deviation of the process so that the variation observed in the output can be reduced. It is one of the two ways in which Six Sigma helps in reducing defects. It is the preferred option if the spread of the process is greater than the tolerance (i.e. Control limits are outside the Specification Limits)


Mean Improvement implies shifting of the process average closer to the target value. It is one of the two ways in which Six Sigma helps in reducing defects. It is the preferred option if the process mean is not equal to the target value


An application oriented question on the topic can be seen below.


Review the answer provided by Mr. Vishwadeep Khatri, Founder CEO, Benchmark Six Sigma


Q 219. Six Sigma helps us improve the process either by reducing the variation and/or improving the mean. Is it mandatory to first reduce variation and then improve the mean? Support your answers with examples



Note for website visitors - Two questions are asked every week on this platform. One on Tuesday and the other on Friday.

Link to post
Share on other sites

1 answer to this question

Recommended Posts

  • 0

Whether we want to improve mean or reduce variation first is entirely dependent on the expectations from process, the current situation and the cost-benefit analysis. Let us see some scenarios - 


  • If specification limits are one sided and shift in mean is easier and cheaper, it makes sense to shift mean. 
  • If specification width (tolerance) is small, it will make sense to reduce variation first as just the shift of mean will not provide a consistent outcome over time. 
  • If specification width (tolerance) is large, shifting mean (if feasible and low cost) may be sufficient and reducing varion may not be needed. 
Link to post
Share on other sites
This topic is now closed to further replies.
  • Who's Online (See full list)

    There are no registered users currently online

  • Forum Statistics

    • Total Topics
    • Total Posts
  • Member Statistics

    • Total Members
    • Most Online

    Newest Member
  • Create New...