OpenMx Help
MaximilianStefan
Joined: 12/04/2018
Performance regression of OpenMx for simple CFA model
I specified a simple CFA model (5 factors, 20 Items each), simulated data from it (25 observations for each parameter) and fitted the model in lavaan and OpenMx. Surprisingly, OpenMx takes about 100x longer to fit the model (same starting values in lavaan and OpenMx). I attached an MWE.
The results on my machine are
lavaan: 0.16 seconds/31 iterations
OpenMx: 13.2 seconds/135 iterations
pgok
Joined: 11/13/2019
Estimating a non-linear model in OpenMx
Hi, I'm pretty new to OpenMx, having only used it off-and-on over the past few years. That said, I am pretty interested in using it more, especially given the multilevel modeling capabilities (e.g., as discussed in Pritkin et al., 2017). However, my question isn't about the multilevel modeling capabilities, my question is about fitting non-linear models.
- Read more about Estimating a non-linear model in OpenMx
- 5 comments
- Log in or register to post comments
Mike Cheung
Joined: 10/08/2009
Comparing raw data and covariance matrix as inputs
Hi,
I am comparing the models using raw data versus summary statistics as inputs. First, let us consider a simple regression model (see the attached example). The model fit should be perfect with df=0. With the raw data as inputs, the chi-square statistic is 2.103206e-11, which is quite reasonable.
When the summary statistics (covariance matrix and means) are used as the inputs, the chi-square statistic is -0.01006717, which is relatively big.
- Read more about Comparing raw data and covariance matrix as inputs
- Log in or register to post comments
Mike Cheung
Joined: 10/08/2009
Fixing the parameter estimates at the starting values
Hi,
I want to fit a model by using the starting values as the parameter estimates. This can quickly be done by treating them as fixed parameters. However, I also want to get some standard errors on these estimates though the starting values may not be the optimal solution.
I can fix the starting values as the estimates with `mxRun(my.model, useOptimizer = FALSE)`. But it does not provide any standard errors. Attached is an example. Any suggestions? Thanks in advance.
Mike
cjvanlissa
Joined: 04/10/2019
Get all log likelihoods from mxTryHard() extratries
Dear all,
is it possible to obtain the log likelihoods from all tries of mxTryHard()? It prints a lot to console, but I can't find this information in the returned object.
Thank you kindly,
Caspar
Andre Achim
Joined: 02/10/2021
mxCI() not providing the confidence intervals. Why?
mxCI() not providing the confidence intervals
jhl12
Joined: 12/14/2020
Installing error on Stampede2
Dear Forum,
I have been trying to install OpenMx on the TACC Stampede2 server and it kept failing. Could you please help?
I need OpenMx primarily to use metaSEM package.
Here is the information you may need.
Platform: x86_64-pc-linux-gnu (64-bit)
R version 4.0.3 (2020-10-10)
I have tried: (1) install.packages(OpenMx) & (2) source('https://vipbg.vcu.edu/vipbg/OpenMx2/software/getOpenMx.R')
Both did not work. The main error message I received was:
- Read more about Installing error on Stampede2
- 5 comments
- Log in or register to post comments
IvanVoronin
Joined: 08/18/2013
CIs are NA but their status is OK - is this OK?
Hello OpenMx community,
I am trying to compute confidence intervals for the parameters that I define as matrix algebra
summary(model) gives the following (only CIs showing):
MaximilianStefan
Joined: 12/04/2018
Parallelization of the objective function for definition variables
We are currently trying to benchmark our SEM software against OpenMx for a SEM with unique definition variables per person.
With ML estimation, because there is a unique model-implied covariance matrix per person, which has to be inverted per person, I assumed that parallelizing the objective function should improve performance drastically. However, changing the number of threads does not change the performance - so I assume I probably did something wrong. I followed this wiki pages instructions:
sar2259
Joined: 11/10/2020
Automation of monophenotype analyses
Hello,
please could you let me know whether it is possible to automate monophenotype analyses ( and also when adjusting for age and sex)?
I was searching whether this might be possible, and found one similar question (https://openmx.ssri.psu.edu/node/4673) with very similar code to what I am currently using. However, it is unclear whether it is possible to do this or not. I have 142 monophenotypes I need to calculate heritability for.
Thank-you.
- Read more about Automation of monophenotype analyses
- 1 comment
- Log in or register to post comments