Six Sigma – iSixSigma Forums Old Forums General IMR CHART QUESTION

This topic contains 2 replies, has 3 voices, and was last updated by  lin 12 years, 5 months ago.

Viewing 3 posts - 1 through 3 (of 3 total)
  • Author
  • #46967


    when i run a imr chart with a set of data based on a sampling plan (every third lot) the data shows within control. However, if I put the data together without the gap, the last data in out of control. Why does this happen, what is the data trying to tell? Here is the data.
    224.7, 226.7, 227.2, 225.5, 225.9, 226.4, 227.0, 223.3, 225.8, 225.5, 224.5, 224.6, 226.0, 226.7, 227.1, 228.4, 227.0, 226.5, 227.0, 227.9, 229.6
    1) put them in minitab with two gaps between the number (in control)
    2) put them without gaps (the last data is out of control)


    Erik L

    If you put the data into a Run Chart (Stat>Quality Tools>Run Chart), I believe that you’ll see the answer to your question.  By placing the data with a lag factor of 2 you actually have two potential issues.  First, the lag factor takes the data and actually impacts you with positive autocorrelation.  Second, the staggered data is much more homogenous then if you took the data point to point.  The last data point falls outside of the control limits due to the artificial tightening of the within sources of variation through estimating standard deviation through MRbar/1.128.  
    There are statistically significant signals for clusters and trends.  Time series analysis would be more insightful through ARIMA modeling of the data.  Hope this helps with insight…



    If you analyze the data without lag, there are a number of out of control situations.  Point 8 (223.2) is just below the LCL (also out on the range chart).  The last 8 points in a row are above the average with the last one being above the UCL.  It appears something has caused the average to move up for those last 8 points – a special cause of variation.

Viewing 3 posts - 1 through 3 (of 3 total)

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