+ Reply to Thread
Results 1 to 5 of 5

Thread: 2 Way ANOVA or multiple t tests with correction?

  1. #1
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Posts
    2
    Thanks
    1
    Thanked 0 Times in 0 Posts

    2 Way ANOVA or multiple t tests with correction?




    Hi all,

    I am trying to do some data analysis, and I'm not sure whether to use a 2 way ANOVA or multiple t tests with Bonferroni correction.

    I am looking at the effect of a chemical on bacterial binding to different polymers. So for each polymer, I want to know if there is a difference in binding between the treatment group and the control group.

    I initially wanted to do a 2 way ANOVA with multiple comparisons because I have two independent variables (polymer and treatment group) and one dependent variable (bacterial binding). However, would multiple t tests with correction be more appropriate if I am only comparing each polymer +/- treatment, and not comparing the polymers to each other?

    I really hope a 2 way ANOVA with multiple comparisons is ok for this data, because I have spent a LONG time making all my figures using the ANOVA data....

    Thanks in advance for you input!!!
    Last edited by jfar18; 07-10-2017 at 05:39 PM. Reason: spelling

  2. #2
    Fortran must die
    Points: 62,031, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,538
    Thanks
    693
    Thanked 916 Times in 875 Posts

    Re: 2 Way ANOVA or multiple t tests with correction?

    Why would you not compare the impact of the polymer on the DV? I can't see any advantage if that is an IV.

    In general ANOVA is recommended to multiple t test, although I have not seen anyone do what you are.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  3. The Following User Says Thank You to noetsi For This Useful Post:

    jfar18 (07-10-2017)

  4. #3
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Posts
    2
    Thanks
    1
    Thanked 0 Times in 0 Posts

    Re: 2 Way ANOVA or multiple t tests with correction?

    Thanks for your response!

    I do want to look at the impact of the polymer, but I only want to compare each polymer to itself +/- treatment, not to the other polymers. So the experimental design is "for each polymer, is there a difference in binding +/- treatment?" I am not looking to see if the binding differs between polymers.

  5. #4
    Fortran must die
    Points: 62,031, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,538
    Thanks
    693
    Thanked 916 Times in 875 Posts

    Re: 2 Way ANOVA or multiple t tests with correction?

    It seems then that you are in practice running one predictor (treatment)within each "group" (the specific polymer). That is one regression for each polymer. In that case ANOVA and single t test should generate identical results - its your choice which you use.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  6. #5
    TS Contributor
    Points: 12,501, Level: 73
    Level completed: 13%, Points required for next Level: 349
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,491
    Thanks
    162
    Thanked 334 Times in 314 Posts

    Re: 2 Way ANOVA or multiple t tests with correction?


    hi,
    I think you would not need the Bonferroni correction in this case, though this is an interesting question.

    regards

+ 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