RE: Prediction

["Prevette, Steven S" <Steven_S_Prevette@rl.gov>]

 Question: I don't quite understand.  One of the things I do is to
monitoring the level of defects, and using regression for estimating the
level for the next year.  To check whether the prediction method is
statistically stabil, I use SPC.  Do you mean it would be more efficient
to plot annual differences and use SPC directly?  What if the regression
seems to be exponential rather than linear?

Suggested Answer:  If you have done the regression properly, the
residuals should be normally distributed, with an average of zero.  Does
not matter how non-linear the regression is.


Steve Prevette
Occupational Safety and Health
Fluor Hanford, A Fluor Government Group Project
ASQ Certified Quality Engineer
steven_s_prevette@rl.gov
509-373-9371