|
|
1 categorical variable vs 2 categoric... |
|
Message/Author |
|
Vlad posted on Thursday, October 29, 2009 - 7:32 am
|
|
|
Hello, I have conducted FA and results shows that 2 factors are enough to explain all variables. Then I would like to estimate LCA. But I have questions: 1)Should I specify 1 or 2 categorical variables? 2)If 2 cat.variables then what statistics, except criteria, should I use to decide the proper number of classes for each cat.variable(LMR and Bootstrapped LR tests are not availble any more)? 3)Can be you recommend me paper for LCA with 2 cat.variables? Regards, V |
|
|
I would use one categorical latent variable and look at different numbers of classes for that variable. You should look at BIC, TECH14, TECH11, loglikelihood etc. and theory. |
|
Back to top |
|
|