I'm using the afex package and lme4::emmeans to analyse a 2-way repeated measures experiment, but the models generated by afex::aov_car remove any subjects for which there is any missing data. Is there a way to change this or is it inevitable with R's anova functions?
Any help would be appreciated. I know I can use the nlme package to model missing data, but it does not offer an easy solution to testing and correcting for non-sphericity.
Thanks in advance!