OpenMx Structural Equation Modeling

Posted on
Picture of user. Ben Joined: 06/20/2023

General strategies to deal with non-convex Hessian matrix

Hello everyone!

I am working on a org psych paper that is currently under review. **The model** is a quite complex *multilevel mediation SEM*, featuring *four latent variables* (only one is exogenous/independent, the others are endogeneous mediators/outcomes). I also include the *measurement models* for each variable (i.e., the respective items as manifest variables). Until now I have done the estimations in a 2-level model using lavaan. For the review I am trying to add a third level to control for further nestedness.

Posted on
Picture of user. pehkawn Joined: 05/24/2020

Understanding runHelper() error: MxExpectationRAM: latent exogenous variables are not supported

I've been trying to modify [this example](https://github.com/OpenMx/OpenMx/blob/master/inst/models/nightly/mplus-ex9.23.R) from OpenMx' repos for testing. For this purpose, I am trying to fit the model using WLS. However, this returns the following error message:


Error in runHelper(model, frontendStart, intervals, silent, suppressWarnings, :
MxExpectationRAM: latent exogenous variables are not supported (x -> sw)

Posted on
No user picture. Hasan Joined: 03/07/2023

Moderated bivariate ACE

Hello,
I'm trying to fit a moderated bivariate ACE model such as the one seen in the attached picture.
Is there a way to do this in umx? As far as I can tell, neither umxGxE nor umxGxEbiv do exactly this. Can they be expanded to fit this particular model?
I've tried to get my head around using OpenMx rather than umx, but with little success :-) But I found this script from the Boulder materials - https://vipbg.vcu.edu/media/course/HGEN619_2015/twin2ModBivAceCon.R, am I correct that this fits the model I'm trying to fit?
Thanks!
Posted on
No user picture. cjvanlissa Joined: 04/10/2019

How to specify a random intercept cross-lagged panel model in OpenMx?

Dear readers,

I am trying to specify an RI-CLPM in OpenMx. However, if I constrain the variance of the observed indicators to zero, the model implied covariance matrix is not positive definite - but these variances are supposed to be zero, as they are partialized into a time-invariant component and a time-variant component. E.g., the variance x1 <-> x1 should be split up into RIx <-> RIx and cx1 <-> cx1.

Can anyone help me correctly specify this model in OpenMx?

Posted on
No user picture. ppl Joined: 01/12/2023

Maximum Likelihood for Cross-Lagged Panel Models with Fixed Effects - Allison et al. 2017

Hey all,

I just started recently to use OpenMx for academic reasons. I'm currently trying to reproduce the empirical example of the paper of Allison et al. 2017 in which they use a Maximum Likelihood Structural Equation Model (ML-SEM) for dynamic panel models.
The authors provide the code of the following software packages: R-lavaan, Stata, Mplus, SAS-Proc Calis. However, I'm using OpenMx in R since it seems to be more flexible for changes and adjustments than lavaan.

Posted on
No user picture. Sedat KANADLI Joined: 08/15/2022

Residual Covariance Matrix

Dear Mike,
A colleague and I studied the factor structure of a scale using the metaSEM package. The reviewers asked us for residual covariance matrice of structural model we construct. I couldn't see a command for this in the metaSEM package. There is vcov but this command gives sampling covariance matrices. Is there a way to see residual covariance matrices?
Sincerely

Posted on
No user picture. Roya Joined: 10/25/2021

Non-positive definit matrices

Hello Mike,

I am applying the MASEM method to 70 articles to find the direct and indirect effects of a variable (I have only three variables, one outcome, one exposure, and one mediator). I have 67 non-positive definite matrices. I understand that excluding all those matrices is missing lots of data. What should I do in this case? I did the analysis, ignoring the positive definite assumption, and I got the results but I don´t know how reliable are the results.
I´d be grateful if you please help me to find a solution for that.

Posted on
No user picture. iana Joined: 10/16/2021

How to handle missing data in multilevel meta analysis & mutilevel TSSEM?

Hi Mike and all,

I'm working on a meta-analysis examining the mediators between attachment and intimate partner aggression. I would like to use two methods to meta-analyze the data. The methods include 1) three-level meta-analytic models (Assink & Wibbelink, 2016) and 2) three-level TSSEM (Wilson et al., 2016). Both are random-effects models.

Posted on
No user picture. cllstrauss Joined: 04/07/2022

Random factor loadings in MCFA

Apologies if this is answered elsewhere, but I was wondering if OpenMx allows estimation of random factor loadings at the within-level in a multilevel confirmatory factor analysis.

A less important aside: has anyone been able to successfully include a nonlinear constraint in a two level CFA or SEM with latent variables?

Posted on
No user picture. lf-araujo Joined: 11/25/2020

How to go past a model implied cov not positive definite error?

Hi all,

I am trying to specify the CLPM in the attached figure (It's an extension of Zyphur's 2020 general CLPM, but with PGSs). I specified both using lavaan syntax in umx and matrix algebra (first time, hope it is correct, but looks like so). It is identified, the model runs ok. But when I try to get power or the ncp statistic it fails, as the model's implied cov is not positive definite.

- What can I do to avoid this? lbounds and ubounds will help me there?

Lavaan code: