OpenMx Developer Forums
rgore
Joined: 01/27/2011
Developer's Meeting Notes 6/29/12
At the Developers Meeting on 6/29/12 we discussed the following:
- Tim has the smart hessians working correctly in the OpenMx trunk. Equality constraints remain an open question but are not a common case, so most functionality should be available to users.
- Read more about Developer's Meeting Notes 6/29/12
- Log in or register to post comments
rgore
Joined: 01/27/2011
Developer's Meeting Notes 6/15/12
At the Developers Meeting on 6/15/12 we discussed the following:
- Read more about Developer's Meeting Notes 6/15/12
- Log in or register to post comments
mspiegel
Joined: 07/31/2009
Developers Meeting Notes 6/1/12
This week we discussed the following topics:
1. Tim Brick is implementing analytical gradient calculations in the backend. To prepare for this new feature, we discussed how to revise the mxOptions() to specify which type of gradient calculation is performed.
| Key | Possible Values |
|---|---|
| Calculate Hessian | "Yes", "No" |
| Hessian Type | "Blended", "Analytic", "Numeric", "Both" |
- Read more about Developers Meeting Notes 6/1/12
- Log in or register to post comments
rgore
Joined: 01/27/2011
Developers Meeting Notes 5/25/12
At the Developers Meeting on 5/25/12 we discussed the following:
- The group discussed the release of OpenMx 1.2.4. This binary release addresses many memory leaks that existed in previous releases of OpenMx. The remaining memory leaks seem to exist in mxAlgebra. The group discussed attempting to identify these leaks in the future using the
- Read more about Developers Meeting Notes 5/25/12
- Log in or register to post comments
rgore
Joined: 01/27/2011
Developers Meeting Notes 5/18/12
At the Developers Meeting on 5/18/12 we discussed the following:
- Michael Spiegel has found and patched several memory leaks in the latest release of OpenMx. A new release of OpenMx with fixes for these will be released shortly. The group also discussed automating Valgrind checks for memory leaks into the test process.
- Read more about Developers Meeting Notes 5/18/12
- Log in or register to post comments
mspiegel
Joined: 07/31/2009
omx[Get/Set]Parameters with anonymous free parameters
Since we were cleaning up the saving and loading of models (see http://openmx.psyc.virginia.edu/thread/1385), on a related matter I decided to support anonymous free parameters in the utility functions omxGetParameters() and omxSetParameters(). Anonymous free parameters (free parameters that have a label of 'NA') are now identified by the string "modelname.matrixname[row,col]". This notation will be available as input to the function omxSetParameters(), which currently rejects anonymous free parameters. The following demo will work in OpenMx 1.3.
rgore
Joined: 01/27/2011
Developers Meeting Notes 5/4/12
At the Developers' Meeting on 5/4/12 we discussed the following:
- The group discussed the trajectory of the approach they would like to take to add multilevel modeling capabilities to OpenMx. The group will start with adding hierarchical multilevel modeling capabilities before they any cross classified multilevel modeling capabilities.
- The group discussed progress of the weighted least squares (WLS) implementation for OpenMx. Tim has implemented arbitrary WLS functionality for OpenMx.
- Read more about Developers Meeting Notes 5/4/12
- Log in or register to post comments
mspiegel
Joined: 07/31/2009
Saving and Loading a model
We have been receiving feedback from OpenMx users using save() and save.image() to save the state of a MxModel into a file on disk. There have been problems associated with saving a model from an older version of OpenMx and attempting to load the model into a newer version of OpenMx. save() and save.image() store the internal representation of OpenMx objects, which may change across different versions of OpenMx.
- Read more about Saving and Loading a model
- Log in or register to post comments
Arnond Sakworawich
Joined: 04/28/2012
What is the numerical approximation method used to find maximum likelihood estimator from log-likelihood function in OpenMx?
1.
What is the numerical approximation method used to find maximum likelihood estimator from log-likelihood function in OpenMx?
2. How to deal with multiple estimators when you have to maximize log likelihood function here in OpenMx? Say profile likelihood or partial derivation (may not be the case).
3. Can some of you please provide me a document on how the OpenMx works on the maximization of log likelihood function to find MLE?
Thank you so much.
Arnond
rgore
Joined: 01/27/2011
Developers Meeting Notes 4/27/12
At the Developers' Meeting on 4/27/12 we discussed the following:
- Read more about Developers Meeting Notes 4/27/12
- Log in or register to post comments