# Can I use a residual variable (from a binary variable) as response variable in binomial glmm or glm?

I'm working on Rstudio and I have a question about residues in a binomial glm's case.

• I used a glm to correct my response variable (germination (ger_b), encode 0, 1) by the light, because this variable presents variation inside my treatments.

• Because I want to use treatment and light as explaining variable, I I use the residuals of this as new response variable instead of binary germination.

Here's my code:

C_ger_b <- glm(ger_b ~ lum, family=binomial(link=logit), data=d)
R_ger_b <- residuals(C_ger_b)


My question is : Can I use this new variable in a binomial glm or glmer, even if it's not binary anymore?

Here is my new response variable :

  summary(R_ger_b)
Min.  1st Qu.   Median     Mean  3rd Qu.     Max.
-1.59181 -1.25091  0.84093  0.06977  1.00200  1.25993


Here is my initial response variable :

 summary(d\$ger_b)
Min. 1st Qu.  Median    Mean 3rd Qu.    Max.
0.00    0.00    1.00    0.61    1.00    1.00


I hope my question isn't inappropriate, thank you for your time.