You are here

Error message from mxRefModels ": object 'ordinalCols' not found

2 posts / 0 new
Last post's picture
Joined: 01/31/2016 - 14:18
Error message from mxRefModels ": object 'ordinalCols' not found


I've run into a persistent problem and hoping to get some help/ideas. I'm a newbie running a rather large multi-group model (156 parameters). I'm using a covariance matrix for input and the model converges just fine but when I try to create a reference model, I get an error. While I have some ordinal predictors, I am not sure what the "ordinalCols" object is that the error message is referring to. Apologies in advance if this question has already been addressed before but I have looked through over 10 pages of questions related to errors and haven't seen one resembling this issue. I have provided the output (below) from traceback, omxversion (2.5.2 [GIT v2.5.2]) and r version (R version 3.2.5 (2016-04-14) running on a Windows 10 x64 system). Any and all help welcome....thanks

> refHomo <- mxRefModels(fitHomo, run=TRUE)
Error in generateNormalReferenceModels(modelName, obsdata, datatype, any(!, :
object 'ordinalCols' not found
> traceback()
9: generateNormalReferenceModels(modelName, obsdata, datatype, any(!,
8: generateReferenceModels(x$fitfunction, x)
7: generateReferenceModels(x$fitfunction, x)
6: ReferenceModelHelper(model[[grpnames[i]]])
5: generateReferenceModels(x$fitfunction, x)
4: generateReferenceModels(x$fitfunction, x)
3: ReferenceModelHelper(x)
2: lapply(ReferenceModelHelper(x), function(model) {
if (!isS4(model))
model <- omxAssignFirstParameters(model)
model <- mxOption(model, "Standard Errors", "No")
model <- mxOption(model, "Calculate Hessian", "No")
if (run) {
model <- mxRun(model, silent = FALSE)
1: mxRefModels(fitHomo, run = TRUE)
> mxVersion()
OpenMx version: 2.5.2 [GIT v2.5.2]
R version: R version 3.2.5 (2016-04-14)
Platform: x86_64-w64-mingw32
Default optimiser: SLSQP
> version
platform x86_64-w64-mingw32
arch x86_64
os mingw32
system x86_64, mingw32
major 3
minor 2.5
year 2016
month 04
day 14
svn rev 70478
language R
version.string R version 3.2.5 (2016-04-14)
nickname Very, Very Secure Dishes

AdminRobK's picture
Joined: 01/24/2014 - 12:15

Hmm. Could you post your script?