|
|
 |
| LCA with Discrete-Time Survival Anal... |
 
|
| Message/Author |
|
|
|
|
Hi Dear Drs. Muthen,
I am trying to model a four-class discrete-time survival anlaysis by combining syntax from LCA and discrete-time survial anlaysis together. I notice that I am not able to requset LOGRANK and Plot2 as what I can do in LCA + cox regression.
classes = c(4);
analysis:
type=mixture missing;
Miterations =500;
Mconvergence=0.00001;
LogCriterion=0.00001;
Convergence= 0.00001;
processors=4 (starts);
model:
%overall%
f by w2-w6 @1;
f on c x1-x4;
c on x1-4;
[f];
output: tech1 LOGRANK;
PLOT: TYPE=PLOT2;
I wonder wherether there are alternative codes I should use to recive the logrank test and survival probabilities for each class at different time points?
Thank you very much,
Chien-Ti |
|
|
|
|
| You cannot use a categorical latent variable as a covariate. If this does not solve the problem, please send the output and your license number to support@statmodel.com. |
|
|
| Back to top |
|
|
