Perhaps this could be done by expanding the loading and saving of models to also include past fitting attempts. This way mxTryHard can pick up where left off when interrupted, and I can also page through the solutions of all the tries that mxTryHard made.

Thanks for all the work on OpenMx!

I know about mxSave and mxRestore, but when I run mxRestore I still have to use mxRun to compute all the numerical derivs before I can print a summary() of the model's results. This can take a while if I am reading in many models.

Would it be possible for mxSave and mxRestore to also save/restore the derivs that are computed in the last step? This way I can run a model, save it, and then instantly load it later when I want to work with the results.

Thanks for your time!
Kyle

First, I would like to thank you for all your fantastic work.

I am wondering if the mxBoostrap() could return an object of class boot from the base boot package. A similar facility has been developed in rms::bootcov() function. This capability makes it standard on how to compute the confidence interval using different approaches available in the boot package.

Model Fit Wish list

OpenMx, Mx and other software return multiple fit indices, but a large number exist. This page is a wish-list of indices, how OpenMx or umx computes them.

✓ = returned by OpenMx Summary. ✓(umx) means available via the umx::umxFitIndices function.