I was wondering there is a way to carry out multinomial logistic regression within a structural equation model in R? I am currently using the lavaan package, and so far have not been able to find any discussion on this.
Background info:
My dataset includes answers to survey questions about innovativeness, proactiveness, and risk-taking on a Likert scale. First-order and second-order latent variables are created based on these questions to form the dimensions of innovativeness, proactiveness, and risk-taking and entrepreneurial orientation, respectively. Based on the second-order latent variable of entrepreneurial orientation, I would like to predict the type of employee an individual is. To this end, I am planning to use multinomial logistic regression.
That is why I was wondering if there is a way that I can implement multinomial regression within a SEM model. The lavaan package in R does not have the capacity to work with nominal dependent variables yet. Is there any way that we can work around this?
Hello Vinh Phan,
Also find the attached file, could be helpful.
Cheers.
This is a strange question. I don't understand why you should need such a thing.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling