0
$\begingroup$

In my lab I need to test if there's an significance between male and female sexual dimorphism on body temperature over 40 minutes. The temperature is simulated with a heat lamp and is turned on at 0 minutes and stays the same for the duration of the experiment. I've done multiple trials, and for each trial there's 9 data points collected (temperature collected from male and female every 5 minutes). Is there a model I can fit in R, and a significance test (T-test?) that would fit best for my data? Should I do a permutation test?

Thank you! enter image description here

(Green: Female, Blue: Male)

|cite|improve this question
$\endgroup$
0
$\begingroup$

You should log-transform the temperature to try to linearize it and then do an ANCOVA of the form log(Temperature) ~ Time + Sex.

You might have to try log-transorming time as well, if the log-transformation of temperature alone is not enough to achieve linearity on the temperature-time graph for each sex.

See more info and examples here.

|cite|improve this answer
$\endgroup$
  • $\begingroup$ That might work well, thank you so much! I will look more into it. $\endgroup$ – Michael Lee Apr 29 '19 at 18:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.