Last 3 Days
Regression with Variables (loaded on ...
Structural Equation Modeling
posted on Monday, November 16, 2015 - 11:06 am
Not sure where to post this, so I just started a new thread (sorry).
I was wondering what is the conceptual difference between a simple multiple (logistic) regression, and a regression where my predictors are loaded on latent factors. Does the latter make sense?
Y on X1-X10; !Y is binary
F1-F3 by X1-X10(*1);
Y on X1-X10;
The output estimates were different (Y on X1-X10), but their signs and significance are similar (some became smaller, some became bigger with F1-F3).
What is the effect of loading X1-X10 to F1-F3 in X's prediction of Y?
Can I say that X1-X10's prediction of Y is influenced by F1-F3?
Any input would be appreciated. Thanks!
Bengt O. Muthen
posted on Monday, November 16, 2015 - 2:42 pm
In the model using BY you are imposing a model, that is, putting a restriction on the correlations of the marginal distribution of the 10 x's while the other model allows them to be freely correlated.
The model with BY is a bit strange because you don't relate the f1-f3 factors to other variables such as Y.
Back to top
Add Your Message Here
This is a private posting area. Only registered users and moderators may post messages here.
Enable HTML code in message
Automatically activate URLs in message