Mixture Distribution and Latent Class Models
maugavilla
Joined: 10/19/2021
Row wise log-likelihood contributions from classes
We are working on calculating Vuong LRT between mixture models from OpenMx. Specifically, we are adjusting the function vuongtest() from the package nonnest2.
But we are stuck in one step so far, getting the row-wise log-likelihood contributions to the overall model LL. Because of the structure on OpenMx we are able to get the row-wise contributions for each class, but we havent been able to see how these are combined into the overall model fit
maugavilla
Joined: 10/19/2021
Plans for Mixture model package - help in the process
As part of a bigger project we are working with applications of mixture models. And we have found that no R package provides all the functionality we need. The only programs so far with all the functionality is LatentGold, but this is a propietary and have working with the license has been complicated
rabil
Joined: 01/14/2010
Output from Mixture Model - How to Determine Latent Scores
I've attached a file with the relevant code.
Thanks.
Rick
jeff.harring
Joined: 05/11/2012
Training Data
- Read more about Training Data
- 2 comments
- Log in or register to post comments
Aivil
Joined: 03/14/2019
Example Scripts for Latent Class Growth Analysis (LCGA)??
Are example scripts available for Latent Class Growth Analysis (LCGA) in OpenMx?
Many thanks!
Aivil
Joined: 03/14/2019
3-class Mixture Model : Help to find Starting Values for each class!!
I am currently try to fit a 3-class mixture model on longitudinal data. I'm having a hard time understanding how I should set the starting values for each class.
As far as I understood from Chapter 7 of "Growth Modeling" (Grimm, Ram & Estabrook, 2017), p.150, starting values should be different for each class.
I have tried using the mxTryHard() function to set the best fitting starting values, but it seems there is no difference in the outputs with or without that function.
Aivil
Joined: 03/14/2019
Associative Growth Mixture Model in OpenMx
Is it currently possible to implement an Associative Growth Mixture Model in OpenMx? I was having a look at this paper from Hix-Small et al. (2004) where the authors are combining a multivariate LGM and a GMM to simultaneously
study the relationships among alcohol and marijuana use over time and investigate the existence of sub-populations.
I will probably need this approach to analyze my data, so just wondering if there is an alternative to Mplus.
Thanks
- Read more about Associative Growth Mixture Model in OpenMx
- 3 comments
- Log in or register to post comments
Aivil
Joined: 03/14/2019
Associative Growth Mixture Model in OpenMx
Is it currently possible to implement an Associative Growth Mixture Model in OpenMx? I was having a look at this paper from Hix-Small et al. (2004) where the authors are combining a multivariate LGM and a GMM to simultaneously
study the relationships among alcohol and marijuana use over time and investigate the existence of sub-populations.
I will probably need this approach to analyze my data, so just wondering if there is an alternative to Mplus.
Thanks
- Read more about Associative Growth Mixture Model in OpenMx
- Log in or register to post comments
KB
Joined: 12/19/2018
Latent Profile Analysis / Finite Mixture Model
I have been following the other post about latent class analysis using EasyMx [https://openmx.ssri.psu.edu/comment/reply/4282/7227](https://openmx.ssri.psu.edu/comment/reply/4282/7227). I still have some questions and concerns. My goal is to run a two component finite mixture model (aka Latent Profile analysis with two classes).
Is the optimization being done gradient descent or some other algorithm like EM algorithm. I would like to be using the EM algorithm.
ZZ
Joined: 07/22/2018
Example Scripts for mxComputeEM?
I wonder if anybody could share example scripts involves using mxComputeEM?
The only sample code I found is in paper by Paritikin, Hunter, and Boker 2015 conducting item factor analysis https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4822086/, where mxComputeEM is called with arguments: "expectation = , predict = ". However, as the help file (version 2.11.5) of mxComputeEM suggests, these two arguments are deprecated, and an argument called "estep" should be used.
- Read more about Example Scripts for mxComputeEM?
- 3 comments
- Log in or register to post comments