+ Reply to Thread
Results 1 to 2 of 2

Thread: Correcting alpha for multiple anovas

  1. #1
    Points: 29, Level: 1
    Level completed: 58%, Points required for next Level: 21

    Thanked 0 Times in 0 Posts

    Correcting alpha for multiple anovas


    I have 7 different properties, all independent, that are being mesured. Each property has a control and three disease groups. All independent. With each property, I compare the 3 disease groups to the control, but not the disease groups to eachother. I do this with ANOVA + Dunnett's test. So I have 7 ANOVAs.

    My problem is that I'm not sure how I should correct for multiple testing because I have 7 ANOVAS. Right now I do a Benjamini-Hochberg process for 7 measurements to correct the alpha for the p-values of the ANOVAs, then I just do the Dunnett's tests (in the ANOVAs that still have significant p-values) with no further correction. Is this correct?

    Thank you!

  2. #2
    TS Contributor
    Points: 8,362, Level: 61
    Level completed: 71%, Points required for next Level: 88

    Crete, Greece
    Thanked 35 Times in 34 Posts

    Re: Correcting alpha for multiple anovas

    Even a simple Bonferroni is enough, since you only have 7 pvalues. Dunett's contronls the family wise error rate?

+ Reply to 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