• This topic has 2 replies, 3 voices, and was last updated 18 years ago by DD.
Viewing 3 posts - 1 through 3 (of 3 total)
  • Author
  • #37142


    Hi,  I need your help to analyse the meaning of this information given by minitab for a DOE project:
    I understand nothing its important due we have a P value bigger than 0.05 in all factors, but I dont know if  my conclusion is right. We have an error of 3%, so the model is complete.

    General Linear Model: Yield versus Layers, Method, Blocks

    Factor     Type Levels Values
    Layers    fixed      4 0 1 2 3
    Method    fixed      2 1 2
    Blocks    fixed      3 1 2 3

    Analysis of Variance for Yield, using Adjusted SS for Tests

    Source                DF                     Seq SS        Adj SS           Adj MS         F         P
    Layers                   3                  0.0008050     0.0008050     0.0002683    1.89      0.249
    Method                  1                0.0000707      0.0000566     0.0000566    0.40      0.555
    Blocks                   2                 0.0001656      0.0001439     0.0000719    0.51      0.630
    Layers*Method    3               0.0000158      0.0000116     0.0000039    0.03      0.993
    Layers*Blocks    6                 0.0003949      0.0003841     0.0000640    0.45       0.819
    Method*Blocks    2               0.0002023      0.0002023     0.0001012    0.71       0.534
    Error                      5                 0.0007085      0.0007085     0.0001417
    Total                     22  0.0023627 

    Unusual Observations for Yield  

    Obs     Yield       Fit      SE Fit  Residual   St Resid
      4   0.99530   0.99530     0.01190  -0.00000         * X

    X denotes an observation whose X value gives it large influence.


    Robert Butler

    There are a number of things you might want to consider before concluding you have no significant effects.
    1. Your response is yield.  If all of your data is in the form of 99.XXX then what you are really looking for are factors impacting XXX.  drop the 99 and rerun the regression on X.XX and see if you get the same result. 
    2. Are your factors discrete or continuous?  If they are discrete, did you code them properly for use in the regression package? If they are continuous why haven’t you checked at least for the squared effects of all three?  Did you set up the design to check squared x whatever interactions?  If you did, where are these terms?
    3. With the existing model did you check your plots of residuals against predicted as well as against all of the X’s?  If you didn’t you should – you may find some surprising plots that might point you in the direction of a solution.
    4. You say “We have an error of 3%, so the model is complete” – what does that mean?  A 3% error, if all measures are 99.XXX , sounds like it might exceed the entire range of the response.



    Hi GB,
    Apart from what robert has suggested please check your Measurement system. Have you done Gage R&R/bias/accuracy/linearity/stability whichever is applicable. I feel there could ba a Gage issue somewhere in your measurement.

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

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