I am trying to create a plot of predicted probabilities from a generalised multilevel linear model (random intercept) using sjPlot package. I want to plot the effect of an interaction term. I am attempting to change the C.I. level, which I assume is 95% by default (the documentation of the package is not very clear about this…). However, the C.I.s do not seem to change. I reproduced what I am trying to do using the iris dataset, to show what I mean. Below you can find the code: