Hello all

I have a question regarding choosing a reference category in MNL regression.

I explained here briefly what is the type of my dataset and what I am doing.

I have a categorical dataset. my dependent variable has 4 classes; Very Satisfied, Rather Salified, Rather Dissatisfied, and Very Dissatisfied. I selected 'Very Dissatisfied' as a reference group for Multinomial Logistic regression which has the lowest frequency (but not very small to have an unstable estimate). And my research question is to assess the satisfaction level of users on pedestrian streets. Is that right to justify the reason why I have chosen this particular class as a reference category that I wanted to examine how different satisfaction levels compared to the lowest level of satisfaction? Could you please tell me whether I am right or wrong in this situation?

Many thanks

Similar questions and discussions