Just Plot the Data – It is So Simple!

Quick Links

SPC for Excel Software

Visit our home page

SPC Training

SPC Consulting

Ordering Information

Thanks so much for reading our publication. We hope you find it informative and useful. Happy charting and may the data always support your position.


Dr. Bill McNeese
BPI Consulting, LLC

View Bill McNeese

Connect with Us

Comments (5)

  • AnonymousMay 30, 2013 Reply

    Dear Bill,If I had the power, I would nominate you for the Nobel Prize! Your newsletters are simply brilliant. They explain stats in such a simple practical manner. Keep up the good work. Best regards, Shankar ShridharMelbourne, Australia

  • AnonymousMay 30, 2013 Reply

    Hi everyone,Another way to look at this would be to not stage the last 4 data points, then only 2009 would show as an exceptional increase, the remaining data points staying within the limits of stage two.Take care not to stage just to tell "your" story or to "fit" the data!Best regardsPierre

    • billMay 30, 2013 Reply

      Hi Pierre,Thanks for the comment.  Yes, I thought about looking at the data without the third stage.  Actually, if you base the limits on the 2002 to 2008 data as a trend chart, then 2009 data point is just below the UCL.  The other three remain within the those limits as you state.  The reason I didn't do that was because there was a process change that year with the increase in spending to bail out the banks (among other items).  And the results in spending from that year onward represent the first time spending has not increased each year – so that trend was broken.  It may not have failed one of the classical test for out of control, but that appeared to me to be a significant process change.  So, that is why I went with the third stage. 

  • AnonymousMay 31, 2013 Reply

    Hi Bill,Would you please explain how you managed to get the trend lines in figure 3 ? Regards, Rahul

    • billMay 31, 2013 Reply

      The calculations for the trend control chart are the same for the individuals chart except  for the average line.  The value of the average line is the best fit line: Y = b1X + b0 where b1 and b0 are constants determined by regression.    Y is the center line (X double bar), e.g., the spending for that year; and X is the year.<br /><br />So,<br />UCL  = Y + 2.66Rbar = b1X + b0 + 2.66Rbar LCL  = Y – 2.66Rbar = b1X + b0 – 2.66Rbar<br />where Rbar is the average moving range of 2.

Leave a Reply

Your email address will not be published. Required fields are marked *