Developers Meeting 1/15/10

2 replies [Last post]
mspiegel's picture
Offline
Joined: 07/31/2009

Here are the minutes from today's developers meeting.

  1. write a different mxThresholds() conformability checking when there are multiple matrices/algebras
  2. add a special case for a logical vector of NAs
  3. set function precision for the ordinal case to 1e-09
  4. can we add constants to constraints?
  5. look at filling in the values for diagonal matrices
  6. implement d2v() function
  7. implement v2d() function
  8. add to the summary() and output the OpenMx version number
  9. write a function that prints the covariance and means matrices
  10. give Tim and Mike N. administrative access to website
  11. confidence intervals?
  12. use an explicit hessian computing function?
  13. document the SaturatedLikelihood argument to summary()
  14. print the labels matrix with free and fixed designation
mspiegel's picture
Offline
Joined: 07/31/2009
Update: write a different

Update:

  1. write a different mxThresholds() checking (FIXED for single matrix or algebra)
  2. add a special case for a logical vector of NAs (DONE)
  3. set function precision for the ordinal case to 1e-09 (DONE)
  4. can we add constants to constraints?
  5. look at filling in the values for diagonal matrices (RESOLVED)
  6. implement d2v() function (DONE : diag2vec)
  7. implement v2d() function (DONE: vec2diag)
  8. add to the summary() and output the OpenMx version number (DONE)
  9. write a function that prints the covariance and means matrices (DONE)
  10. give Tim and Mike N. administrative access to website (DONE)
  11. confidence intervals?
  12. use an explicit hessian computing function?
  13. document the SaturatedLikelihood argument to summary() (DONE)
  14. print the labels matrix with free and fixed designation (DONE)
neale's picture
Offline
Joined: 07/31/2009
Per the alternative Hessian

Per the alternative Hessian routine, see http://openmx.psyc.virginia.edu/sites/default/files/issues/omxTest2.R, part of the thread http://openmx.psyc.virginia.edu/issue/2009/12/alternative-estimate-hessian

Nice going on the showMeansCovariances helper function! I tend to yearn for such helper functions to be added as part of the OpenMx package, rather than having to run them manually. If that isn't going to happen, how do we decide what to keep as core, and what embellishments to add? And how best to administer them? Would we want OpenMx-helpers as a separate package?