I have collected a nested data measuring cell growth which has two levels (3 patients with disease A, another 3 patients with disease B, another 3 patients with disease C). For each patient, cell growth was measured repeatedly to minimise random error in the experiment.
I would like to access whether cell growth differs by disease groups.

However, considering the small sample size and non-normality of the data, I think that using mixed model may not be appropriate: Is there nonparametric alternative of mixed model where I may analyse non-normally distributed data?

  • 1
    $\begingroup$ Normality of data is not an assumption of (generalized) linear models. $\endgroup$ – user2974951 Aug 8 at 9:16

Your Answer

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

Browse other questions tagged or ask your own question.