|
|
GMM with binary covariate influencing... |
|
Message/Author |
|
|
Hi, I have a very simple GMM, and I want to add in a binary covariate (gender). I want this covariate to influence the latent class assignment. I am having some problems, and I first want to double check to make sure that I am coding it correctly. Could you take a look at what I have below? DATA: FILE = "C:\mixed.dat"; VARIABLE: NAMES ARE v1 v2 v3 v4 gender; USEVARIABLES ARE v1 v2 v3 v4 gender; CLASSES = c (2); ANALYSIS: TYPE = MIXTURE; MODEL: %overall% I by v1-v4@1; S by v1@0 v2@1 v3@2 v4@3; [v1-v4@0]; i WITH s@0; i*5; s*1; c#1 on strata; %c#1% [i*2.24]; [s*1]; %c#2% [i*6.72]; [s*3]; OUTPUT: stand; |
|
|
You would say c ON gender; |
|
|
Thanks for such a quick reply. Unfortunately, when I tried the "c ON gender" option that you suggested, I got a series of error messages. The first was "Unknown variable: C". And "Variable is uncorrelated with all other variables within class: GENDER". Am I doing something wrong? |
|
|
Can't tell without more information. Please send your input, output, data, and license number to support@statmodel.com. |
|
Back to top |
|
|