Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.

I have the following results from a biological experiment. I measure the size of the sample (2,4,8,16,32 or 64) and count its distribution in a population of 50 (sum of counts=50). I do those measurements in the wildtype (wt) and the experimental sample (KO) in three independent experiments (replicate 1,2,3).

Am I in a setup for a two way ANOVA with replicates? How can I proceed rigorously, with the maximum power in R as I am not sure (1) my data is normally distributed and (2) how to code that in R anyway?

Thanks!

strain  Replicate   size    count
wt  1   2   2
wt  1   4   6
wt  1   8   11
wt  1   16  12
wt  1   32  9
wt  1   64  10
wt  2   2   2
wt  2   4   7
wt  2   8   15
wt  2   16  11
wt  2   32  4
wt  2   64  11
wt  3   2   0
wt  3   4   5
wt  3   8   17
wt  3   16  9
wt  3   32  9
wt  3   64  10
KO  1   2   0
KO  1   4   0
KO  1   8   2
KO  1   16  15
KO  1   32  23
KO  1   64  10
KO  2   2   0
KO  2   4   2
KO  2   8   2
KO  2   16  20
KO  2   32  22
KO  2   64  4
KO  3   2   0
KO  3   4   0
KO  3   8   3
KO  3   16  20
KO  3   32  21
KO  3   64  6
share|improve this question
I think your treatments are wt and KO and there are two responses that you observe for each replicate -- size and count. BTW, I am assuming by replicate you mean biological replicate. If I am right, it is just ANOVA with 1 treatment, but I don't understand the reason for 3 experiments. – suncoolsu Sep 1 '11 at 18:36
Yes, I have 3 biological replicates (replicates 1,2 and 3) to test for reproducibility. Hope that makes more sense. Thanks! – Olivier Sep 2 '11 at 14:32
So, you just have two treatments then wt and KO and you are taking two observations on it, size and count. Right? If yes, I will post the answer. – suncoolsu Sep 3 '11 at 0:33

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.