I have constructed a mixed effect model where one of the predictors is a Y/N presence variable for a certain species. However, the response variable contains continuous summary data (ecosystem food-chain length) that at some sites include values from this predictor species, among other species (I.e., sites with presence of this species tend to exhibit longer food chains).
I have received conflicting opinions on whether this approach is valid, and decided to go forward with the models as-is, because it seems to be an effective way of evaluating the effect of this species' presence on food webs. I am struggling to find examples or citations to back up my position, however. Thus, if anyone is able to offer an opinion or citation of an example one way or the other I would be very grateful!