Hi, I am having problems working out what to do with my data, I have a series of positions (26 for each limb!), nested within a limb (10 of them), nested within a posture (30 of them). I then have 5 observers rating them........so far I have tried lmer and glm but R doesn't want to play. I'm not sure if I'm trying to do the right thing, or if it's my data it doesn't like! Any help with this problem would be much appreciated, just a point in the right direction, or another study that has had to deal with this kind of data! Thanks, Julia. -- View this message in context: http://n4.nabble.com/Inter-observer-reliability-nested-categorical-data-tp976392p976392.html Sent from the R help mailing list archive at Nabble.com.