What question do we want to ask?
Our newest runs!
Depending on our questions, we could apply different tests.
QUESTIONS 1.
Does overall treatment vs. control make a difference (T vs C)?
Does overall how often we kill things off make a difference (A vs B)?
Is there an interaction in how these things apply?
For these three maybe General linear model in the binomial case, can be applied to our data?
QUESTIONS 2.
Is TA different from TB?
Is CA different from CB?
We can use fishers exact test, on TA vs TB independent of CA vs CB.
Fisher's exact test results:
TAvsTB: p=5.37 x 10^-9
CAvsCB: p=.48
CBvsTB: p=0.32
CAvsTA: p=1.04x10^-9
What is the impact of this repeated testing on doing this this way?
COUld you give me a bit more details on the treatments again?
ReplyDeleteIf you are interested in the proportions, you can use a generalized linear model with a logit link function (a logistic regression), which is pretty easy to use, but needs some care with interpretation. I have loads of code that will help from my ZOL851 class where I discuss this. I tend to find it easier to think on the probability scale, and not the logit scale, so I often fit the curve back..
For your second question, I suggest either just doing some bonferroni corrections of the Fishers exact test in this case.
ReplyDeleteIn A's we cut down the population size by 95% every 500 updates.
ReplyDeleteIn B's we did so every 5,000.
In 'treatments' we changed the environment every time we cut down the population,
in 'controls' a randomly selected environment was used for the whole experiment.
I need to read up on logit link- does that work for count data?
Is there something better we could be using to compare the cumulative distributions, rather than the final counts?