In the help file for mxFactorScores, it says:
The rows are in the order of the sorted data.
I'm not sure what this means. The data I have is in order by date and it's clear that the estimated factor scores for "ML" are no longer in the same order. There are two correlated factors each with 2 indicators (and nothing else). How can I get the factor scores into the same order as the rest of the data?
BTW, I'm using OpenMx 2.3.1 under R 3.2.2 (Ubuntu 15.04). mxFactorScores does not work with the RAM model so I converted it to LISREL in order to get the factor scores. (I had this problem before but I don't remember if it was ever resolved.)
Printer-friendly version
Hi: That's an old candidate implementation of
mxFactorScoresJust update to OpenMx 2.5.2
When first drafted, mxFactorScores returned scores in the order of the sorted data. However it now returns the scores in data-order, suitable for adding as columns to your data.
It also now supports RAM.
Thanks. I upgraded to 2.5.2 and I changed the model back to RAM and I still get the same errors:
> cal.fit <- mxRun(cal.model,intervals=TRUE)
Running cal_model with 13 parameters
> fscores.ml.omx <- mxFactorScores(cal.fit,type="ML")
Error in free[i, j] : subscript out of bounds
> fscores.wml.omx <- mxFactorScores(cal.fit,type="ML")
Error in free[i, j] : subscript out of bounds
type = "Regression" does work.
I've attached the code and generated a dataset that shows these errors (at least for me).
I changed back to RAM because the LISREL version caused to mxFactorScores to generate errors.
Sorry about this! Apparently, there's a bug in ML/WML factor scores that does not like models with confidence intervals.
When I commented out the mxCI part of the model, everything worked fine. With the mxCI()'s in there, I got the same error as you. I'll work on a bug fix, but in the meantime making the model without the confidence intervals should fix it.
Here's the issue.
It will be fixed in the next release: http://openmx.psyc.virginia.edu/issue/2016/03/confidence-interval-reference-search-broken
Thanks. I commented out the mxCI argument and it works.