I have a a biological dataset, in which I am fitting the following partial mixed ANOVA model (apologizes for the Matlab syntax):
Baseline_Bio_Data,Post_Bio_Data ~ Treatment_Group*Response_Group + Age + Sex + Baseline_Clinical Scores
Baseline_Bio_Data and Post_Bio_Data are my dependent variables, taken before and following a treatment.
Treatment_Group is a 2 level categorical variable (participants underwent one of two treatments with no randomization)
Response_Group is a 2 level categorial variable (those who responded to the treatment and those who did not)
And Age, Sex, and Baseline_Clinical Scores are covariates I’d like to control for.
Now, this leads to 6 between-level effects (treatment group, response_group, baseline_clinical scores, age, sex, and the interaction term) and 7 within-level effects (time and its interactions with the between-level variables). This leads to 13 estimates in total.
Now, I have to apply the same model to 100 different datasets in total (with each dataset representing a different part of the brain). In my field, the use of False Discovery Rate (FDR) for multiple comparisons correction is common.
My question is: if I am only interested in the effects that contain time, treatment group, and response group (totalling to 7 estimates), and not interested in my covariates, can I only correct only for those estimates I am interested in?
I initially went ahead and corrected for all estimates (applying FDR to a 13 estimate x 100 brain region = 1300 matrix of p-values). Would it be wrong to exclude the estimates of no interest from this matrix?
Thank you in advance.