OpenMx Help

reran some old scripts that used to run fine, but under 1.1 the statement
mxOption(thisOMxModel, "Cold Start", "")
now gives the error
"argument 'key' has a value 'Cold Start' that cannot be found in getOption('mxOptions')"

has that been deprecated?

greg

With the release of OpenMx 1.1, I started playing around with the new joint ordinal-continuous feature. We had just done a bivariate ACE model for two phenotypes (one ordinal, 3 levels, and one continuous, which we divided into 10 levels) using Classic Mx.

Hi all, I'm kind of a noob so please forgive me if this is terribly rudimentary.

I get the error message:

Error in runHelper(model, frontendStart, intervals, silent, suppressWarnings, :
BLAS/LAPACK routine 'DPOTRF' gave error code -4

Traceback yields:

3: .Call("callNPSOL", objective, startVals, constraints, matrices,
parameters, algebras, data, intervalList, communication,
options, state, PACKAGE = "OpenMx")
2: runHelper(model, frontendStart, intervals, silent, suppressWarnings,
unsafe, checkpoint, useSocket, onlyFrontend, useOptimizer)

hi all,
If you do "summary(fit)$CI" you get the upper, lower, and estimate:
lbound estimate ubound
top.a_std[1,1] -0.68048731 -0.6216239 -0.5515234

but "fit@output$confidenceIntervals" gives just the upper and lower:
lbound ubound
top.a_std[1,1] -0.68048731 -0.5515234

Because summary takes ages to run on big models, it would be nice if "fit@output$confidenceIntervals" had the estimate in there as well: Also good for consistency.

Best, t

Hi guys,

I'm trying to fit a saturated model where the variable, 'manifests', includes all of the variables in the model. The non-saturated structural model runs fine, but I get an error when I fit the saturated model:

Error: The job for model 'Saturated Model2' exited abnormally with the error message: Expected covariance matrix is not positive-definite in data row 79 at iteration 0.

I am still getting used to OpenMx, so this may be a stupid question. Say I have a single factor ("G") measurement model, in a mxModel object called "mMeasure". Is it now possible to use the mMeasure object as part of a structural model? I imagine something like (pseudocode):

mStructure <- mxModel("Structure",
manifestVars = "Y", latentVars = "G",
mxPath(from = "G", to = "Y"),
## other model stuff)

mFull <- mxModel("Overall",
type = "RAM",
mxData(mydata[, c("all", "manifest", "variables", "for any submodel")], type = "raw"),
mMeasure,
mStructure)

Dear all,
I am doing a simulation. Nevertheless, some of its replications have a warning massage of NPSOL none-zero status code, such as: "In model 'Cross Lagged Model3' NPSOL returned a non-zero status code 6. ... "

Since it is important for analyzing the simulation results, how can this status code be written in the simulation output file?

Here is some part of my input list for producing the output file.

### 5.3 Processing
#####################
modelFit3 <- mxRun(model3)
sfit3 <- summary(modelFit3)
### 5.4 Saving Results
#########################

I usually have problems in installing OpenMx in Fedora 15 with
source('http://openmx.psyc.virginia.edu/getOpenMx.R')

My guess is that Fedora 15 uses gcc4.6 while OpenMx comes with gcc4.4. The following is the error message:
checking for inst/npsol/linux/x86/gcc4.6/libnpsol.a... no
configure: error: npsol library not found
ERROR: configuration failed for package ‘OpenMx’

I am adapting the attached bivariate script to a 4-variable version. I have expanded the X, Y, and Z matrices to to 4-variables, changed Y to accomodate and AE model. After the follow part of the script:

#### DZ Model Stuff ####
mxModel("DZ",
#Pull out data and covariates for DZs
mxData(data.frame(dzData,dzDefs), type="raw" ),
mxMatrix( type="Full", nrow=1, ncol=ndef, free=FALSE, labels=c("data.age_T1","data.SITE_T1"), name="D1"), #twin1 (N)

Sorry folks. I've not been using R or OpenMx for about a year and am very rusty. Just tried to update to latest OpenMx. Seemed to work and I can see the folder for OpenMx in my R library directory, but I get error message if I require(OpenMx). So console is as follows:
> source('http://openmx.psyc.virginia.edu/getOpenMx.R')
trying URL 'http://openmx.psyc.virginia.edu/packages/bin/windows/contrib/2.10/OpenMx_1.1.0-1764.zip'
Content type 'application/zip' length 2298749 bytes (2.2 Mb)
opened URL
downloaded 2.2 Mb

package 'OpenMx' successfully unpacked and MD5 sums checked