Reliability and SEM

General help and assistance with jamovi. Bug reports can be made at our issues page: https://github.com/jamovi/jamovi/issues . (If you're unsure feel free to discuss it here)
Post Reply
kevinchan0903
Posts: 4
Joined: Fri Oct 25, 2019 6:29 am

Reliability and SEM

Post by kevinchan0903 »

Reliability Analysis
I am calculating the Cronbach alpha for my measures, which have over 100 items. I used the Reliability Analysis under the Factor tab. However, it took ages to calculate. But if I put the same variable into SPSS, it calculated immediately. Is it possible to improve the reliability analysis in jamovi like SPSS?

SEMLj
I just updated my jamovi and all modules. When I use the syntax mode of SEMLj, I usually separate my syntax to make it easier to read, e.g.,
AAA ~
BBB + CCC
However, after updating to the current version, it does not allow me to do so. A message saying
"lavaan-> Idw_ parse_step2(): formula without valid operator at line 1, pos 14..." and I have to edit my syntax to
AAA ~ BBB + CCC
Is it still possible to separate the line? Sometimes, I have many variables and want to make it easier to read.

Thanks
User avatar
mcfanda@gmail.com
Posts: 530
Joined: Thu Mar 23, 2017 9:24 pm

Re: Reliability and SEM

Post by mcfanda@gmail.com »

SEM:

Are you sure that in previous versions of SEMLj you could pass syntax with separate lines? I doubt because syntax parsing never changed across versions.
Anyway, what would you like to achieve is something like this

Code: Select all

X ~
A+B+C +D+E+F
Z~
A+B+C +K
I must add that it does not seem to be very clean as a syntax writing method, but I guess if one has several variables, it could be useful to have one regression declared in a multi-line. I'll find a solution for it
User avatar
mcfanda@gmail.com
Posts: 530
Joined: Thu Mar 23, 2017 9:24 pm

Re: Reliability and SEM

Post by mcfanda@gmail.com »

I've just checked, you can achieve what you need as follows:

Code: Select all

X~
+A+B+C
Z~
+A+D+E
kevinchan0903
Posts: 4
Joined: Fri Oct 25, 2019 6:29 am

Re: Reliability and SEM

Post by kevinchan0903 »

Thank you for your suggestion. It works well. Thanks a lot!!
And yes, I am sure I can separate the lines in the previous version as it is easier for me to modify the variables and sort of group like control variables in the first line and other variables in the second line.
Post Reply