Skip to main content
7 events
when toggle format what by license comment
Dec 3, 2014 at 20:05 answer added Meng Hu timeline score: 10
Sep 25, 2013 at 10:31 comment added Peter Flom Hi @gung I was away, I will look at them now.
Jul 6, 2013 at 18:10 answer added generic_user timeline score: 3
Jul 6, 2013 at 15:49 comment added Patrick Coulombe You technically need quite a bit of level-3 units if you're going to get unbiased parameter estimates in a 3-level model (generally speaking, sample size in any multilevel model is particularly important at the highest level), so unless you have a large random sample of countries (50+ perhaps), you should probably consider running separate 2-level models, or if you have few countries, you could consider treating country as a categorical level-2 predictor in a 2-level model
Jul 6, 2013 at 15:36 history edited gung - Reinstate Monica CC BY-SA 3.0
added tag; light editing
Jul 6, 2013 at 15:24 answer added D L Dahly timeline score: 2
Jul 6, 2013 at 12:40 history asked Peter Flom CC BY-SA 3.0