I am analysing my data using GEE in SPSS and would like to ask you a question regarding GEE and ordinal data.
My study dataset includes ordinal data (a 5-point scale ranging from 1 highly unfamiliar to 5 highly familiar). I’ve run a GEE and chose an ‘ordinal logistic’ model but it’s not possible to include ‘EM means’ in this type of model and for this type of data. I would really appreciate it if you could let me know what type of model allows ordinal data to be modeled? a binary logistic model? and if I need to recode my ordinal data?
As a note, my study has a within subject design, where each participant had to complete a familiarity rate test after three different conditions (familiarity rate test after reading a story, familiarity rate test after listening to another story, and familiarity rate test after reading while listening to a story). My dataset includes familiarity score within three conditions and four word frequency (how many times they saw a word in the story; either 1, 2, 3, or 4 times) to examine the effect of different conditions and frequency on participants' familiarity rate.