Problems running CFA
It's been a while since I'd used JASP, so I downloaded 0.18.3 onto my Lenovo Thinkpad 64-bit laptop, imported my data, and specified the model (which involved 9 measures each for four posited factors).
The first problem is that I got a "waiting for the module to initialize" message, so the module was in fact not running. A quick look on the forum suggested that I just needed to close JASP and re-do it. So I saved my JASP file, closed the program, and then re-opened it.
It did bring back the prior module specification, but had a warning that in part seemed to say that there were too many variables in the file. While the CFA I had specified only had 36 variables total, the overall data file has a couple of thousand. Although I couldn't grasp why the CFA module would care about variables not in the model, I decided to use a different file that only had the 36 variables plus an ID measure.
This time I got an error message saying that it could not use categorical data for FIML (or for two-stage or robust two-stage), so I should select a different method for handling missing data. I could do that, but the original data imported from SPSS were defined as numeric scalar data (ordinal, 1-6 strongly disagree-strongly agree), and JASP defines each of my variables as scalar.
So I'm troubled by JASP treating the data as nominal. If I switched missing data to listwise deletion (or pairwise), the output would appear, but with a caution that "the test statistic is scaled shifted [sic] because there are categorical variables in the data," so this misconception is persisting across all missing data specifications. I've been able to run descriptive statistics on the same variables with no problem; there are missing data, because these results come from three waves of a longitudinal panel survey, but that should neither affect how the data are classified nor the CFA, as only those people who appear in all 3 waves for these variables should be included in the latter.
Any suggestions on resolving this?
Branden
Comments
When I tried to add "Additional Output" to the CFA, I then got the following error message:
"This analysis terminated unexpectedly. Error in diag(scales) %*% truevar: non-conformable arguments.
Stack trace"
Furthermore, when I tried to report this as a bug to JASP, it turned out that the guide to submitting bug reports was out-of-date, as I could not find the green button on which to submit the form after searching for similar prior reports.
Branden
Sounds like an issue for our GitHub page! (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/)
EJ