|
|
Intercept-only model, bivariate corre... |
|
Message/Author |
|
Felice K. posted on Friday, June 30, 2017 - 1:52 am
|
|
|
Dear Dr.es Muthen, I want to run a twolevel analysis without predictors on level 1 or 2, just considering the nested structure of the data. The objective is to get the correlation coefficients of 2 dependent variables (CFT-SUM and MC_SUM), the intraclass correlation and the estimated sample statistics for "within" and "between". This is my syntax: data: file = cftmc.dat; variable: NAMES = CFT_SUM klasse MC_Sum; MISSING = all(-99); USEVARIABLES = MC_Sum CFT_SUM; CLUSTER = klasse; Analysis: TYPE = TWOLEVEL; Model: %WITHIN% %BETWEEN% output: sampstat; My fit indices are bad (RMSEA .404, CFI .004, TFL .004), is this due to a syntax error? I get the warnings: "variable is uncorrelated with all other variables CFT-SUM" and "variable is uncorrelated with all other variables MC-SUM". As I have no predictors an level 1 and 2, this is what I intended, isn't it? Thank you for your help! |
|
|
The variables are probably correlated in the data so use WITH on both levels. |
|
Felice K. posted on Saturday, July 01, 2017 - 4:02 am
|
|
|
Thanks a lot for pointing that out! |
|
Back to top |
|
|