I am working with data in which the dependent and independent variables are categorical. Dependent variable has five categories while others have two to four categories. I want to put all in a model so that possible prediction can be made for the dependent. All answers are highly appreciated and welcomed
For count data log linear models and (closely related) Poisson models and variants might be appropriate. For polychromous data it is common to use multinomial logistic regression or ordered logistic regression if the outcomes are ordered. Those options aren't exhaustive!. You'd need to provide further detail to get a more specific answer.
Based on your data, I will recommend multinomial logistic regression. Kindly find links below. Best in your work!
http://www.psychstat.missouristate.edu/Documents/MultiBook3/Mlt07.htm
https://stats.idre.ucla.edu/r/dae/multinomial-logistic-regression/
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis