I am to compare several groups (depressed, bipolar, and controls) on many variables and I was advised to use SEM in R. I am teaching myself R at the moment but I am a bit confused. I am not sure how to proceed. According to my book, invariance is to be used when one wants to evaluate if the structure of the measurement differs across groups or if he/she has genetic data. Is invariance to be used even if all I want is to see differences between the different groups (the means etc.)? Do I create three models (for each group) and compare them?
If you don't have multiple indicators of latent variables (that is, a measurement instrument) but just one observed variable for which you want to compare the means across group, then you don't have the opportunity to check invariance. You can certainly compare the means, but you don't know if they refer to the same construct.
You may want to ask these general questions on SEMNET.
vics gal posted on Friday, February 20, 2015 - 7:08 am
I do have multiple indicators of latent variables, for example, cognitive, hormonal, etc. indicators. I am just very confused about the purpose of the invariance. I wanna see differences between the groups regarding regressions, covariances, etc., and I have many variables so SEM needs to be used.
See the Topic 1 course handout and video where measurement invariance is discussed. If you don't have measurement invariance of latent variables across groups, means and regression coefficients using them cannot be compared.
vics gal posted on Tuesday, March 10, 2015 - 9:25 am
Hi, Thank you for your help. My newest problem is that when I import data into R, all of it is shown nicely, but when I use the 'read.csv(' function, only 223 obs. of 1 variable is shown as opposed to 223 obs. of 140 variables. I understand that the 'read.csv' command is necessary to start working with data.