|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
LPA with only 2 variables |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
Hello, I am running a latent profile analysis using only 2 observable variables. These variables are total scores from 2 measures, one with 28 items and the other with 17. Is it possible to interpret a LPA with only 2 variables? Should I include each item as a separate variable in the LPA? If so, why is that superior to a LPA using 2 summed variables? |
|
|
The model is identified with 2 continuous observed variables. Whether to use the total scores or items should be driven by your substantive agenda. |
|
Back to top |
|
|