+ Reply to Thread
Results 1 to 6 of 6

Thread: Anova

  1. #1
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Anova




    I am trying to find the effects of feed rate, cutting speed and depth of cut on surface roughness. I have five sets of feed rate ( 0.09, 0.10, 0.125, 0.150. 0.175), four sets of speed (41, 53, 66, 82) and two sets of depth of cut (0.5 mm and 1 mm).
    Like: 0.09-41-0.5 = 3.65
    0.09-53-0.5 = 3.41
    ............. Total 40 results (5x4x2)
    As there are different levels associated how can I perform ANOVA ? Do i need to add weights to depth of cut as it has only two sets ? (I am using normal way on Minitab 17 but results were not what I was expecting)
    Last edited by saad2733; 02-29-2016 at 06:13 AM.

  2. #2
    TS Contributor
    Points: 12,287, Level: 72
    Level completed: 60%, Points required for next Level: 163
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,471
    Thanks
    160
    Thanked 332 Times in 312 Posts

    Re: Anova

    hi,
    the problem is imo that you performed each experiment only once, so you have no error degrees of freedom, hence no p-values. Is this your problem?

    regatds

  3. #3
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Anova

    Yes I have performed all the 40 experiments once. When I used anova there is F-value and also P-value but the problem is when I calculated percentage contribution than I got depth of cut as the most significant, but theoretically feed rate should be most significant with the highest F-value. On my experiment there is only two levels of depth of cut and five levels of feed rate, is this the reason behind this ? or different size of levels doesn't matter ? TIA

  4. #4
    TS Contributor
    Points: 12,287, Level: 72
    Level completed: 60%, Points required for next Level: 163
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,471
    Thanks
    160
    Thanked 332 Times in 312 Posts

    Re: Anova

    hi, you mix significance and effect size. Also, the feed rate levels look funny to me, the differences are really small between them, except for the first value. Could you post the analysis here?

  5. #5
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Anova

    Hey I am extremely sorry for porsting feed rate values wrong mistakenly.
    I worked with 0.09, 0.10, 0.125, 0.15 and 0.175. I am sorry for the mistake. Anyways I am posting the results I got by using 40 data sets ( 5x4x2)
    Analysis of Variance

    Source DF Adj SS Adj MS F-Value P-Value
    Model 8 20.6461 2.5808 645.67 0.000
    Linear 3 19.7631 6.5877 1648.16 0.000
    ap 1 12.0744 12.0744 3020.86 0.000
    f 1 4.8393 4.8393 1210.72 0.000
    Vc 1 2.7808 2.7808 695.73 0.000
    Square 2 0.0941 0.0470 11.77 0.000
    f*f 1 0.0668 0.0668 16.70 0.000
    Vc*Vc 1 0.0273 0.0273 6.84 0.014
    2-Way Interaction 3 0.1290 0.0430 10.76 0.000
    ap*f 1 0.0410 0.0410 10.25 0.003
    ap*Vc 1 0.0564 0.0564 14.12 0.001
    f*Vc 1 0.0317 0.0317 7.92 0.008
    Error 31 0.1239 0.0040
    Total 39 20.7700


    Model Summary

    S R-sq R-sq(adj) R-sq(pred)
    0.0632219 99.40% 99.25% 98.84%

  6. #6
    Points: 17, Level: 1
    Level completed: 33%, Points required for next Level: 33

    Posts
    4
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Anova


    Problem is depth of cut is showing F-value 3020.86 which is highest among them. But feed rate should be the one with high F-value. I can't find what's the problem here. I am sure that there is some mistake in the approach to ANOVA

+ Reply to Thread

           




Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats