Fix summary error that I created
Find the bug in models failing simplealgebraci.r and correct the bug I introduced. Writing this down so I don't forget.
- Read more about Fix summary error that I created
- 2 comments
- Log in or register to post comments
Find the bug in models failing simplealgebraci.r and correct the bug I introduced. Writing this down so I don't forget.
?omxConstraintRelations
No documentation for 'omxConstraintRelations' in specified packages and libraries:
you could try '??omxConstraintRelations'
The example in the ? file for omxAssignFirstParameters appears to do nothing to the values of A? Also, I wasn't quite sure what "Select one of the current values for each free parameter and use that value." meant...
A <- mxMatrix('Full', 3, 3, labels = c('a','b', NA), free = TRUE, name = 'A')
model <- mxModel(A, name = 'model')
model <- omxAssignFirstParameters(model);
model$A
@labels
[,1] [,2] [,3]
[1,] "a" "a" "a"
[2,] "b" "b" "b"
[3,] NA NA NA
We have migrated OpenMx to a new server!
We think everything is just the way it was before the migration, but please let us know if you notice anything that might have been broken or lost in transit.
The new server should give us better uptime.
This is a bugfix release for the OpenMx binary. Several bugs were affecting the confidence interval calculations. Please upgrade to this version of the OpenMx library. You should read the announcement for 0.3.2 if you have not already done so.
hi,
requested mxCI(c('top.a','top.c','top.e',
'as11','as22','as33',
'cs11',
'es11','es22','es33')
and got the list below: the items called by label have correctly been found, but in the list, their label is replaced with "reference"
running CIs on a common path twin model, most of the intervals make sense, but some (see example below) are not.
These are all paths which when dropped significantly reduce fit, but it is as iff the optimiser has stepped over zero looking for a worse value, found itself on a nice slope, and concluded that both, for instance + 0.604 AND –0.604 are fine, without seeing that 0 and nearby values are not.
confidence intervals:
lbound ubound
top.a[1,1] 0.6277528 0.7943150
top.as[3,3] -0.6048829 0.6048829
A few changes in this release of the OpenMx binary as we draw nearer to the 1.0 release and the freeze of features.
A mechanism for periodically saving checkpoint files to the local filesystem has been implemented. Using mxRun() with "checkpoint=TRUE" will save a file with the name [modelname].omx to the current working directory every 10 minutes. Use mxOption() to customize some of the behaviors of the checkpoint file (see ?mxOption or the demo "SimpleCheckpoint").
hi,
If the user makes the mistake of using = instead of == in a constraint, they get the error
unused argument(s) (con_a = con_b)
It would be nicer (if possible) to report
Error: A constraint must be of the form: 'exp1 [<, ==, >] exp2'
Example code to generate possible buglet
mxModel("fun",
mxMatrix("Full", 1,1, free=F, values = 0, label="a", name="con_a"),
mxMatrix("Full", 1,1, free=T, values = 1, label="b", name="con_b"),
mxAlgebra(expression= 2*con_b, name="con"),
mxConstraint(con_a = con_b, name="a_eq_b"),
Another milestone towards the OpenMx 1.0 release has been achieved. Likelihood-based confidence intervals can be requested using the mxCI() interface. See the tail end of the following forum post for a discussion on using this new interface.