|
|
New to MLM - Basic help request |
|
Message/Author |
|
|
I am analyzing text from 175 blog posts obtained 16 different medical patients; 8 with one disorder and 8 with another (case code). Some of the blogs for each case are written by the patient and some about the patients by friend or relative (self code) I want to test the main effect of caseness on text parameters (e.g. fm_negemo), as well as the interaction of caseness and self-other on text parameters. Can someone tell me if I have set this up right in the code below. Thanks. USEVARIABLES = Subject casecode selfcode fm_negemo casexself; CLUSTER = subject; BETWEEN = casecode; WITHIN = selfcode casexself; Define: casexself = casecode * selfcode; ANALYSIS: TYPE = TWOLEVEL; Model: %WITHIN% fm_negemo ON selfcode casexself; %BETWEEN% fm_negemo ON casecode ; |
|
|
You have too few cluster units to do multilevel modeling. Some say you need a minimum of 20. Others say a minimum of 30-50. You might want to ask on MultilevelNet how you might handle your data. |
|
Back to top |
|
|