Dear Bayesian model experts, Assuming one has data with 20 categories, multinomial distribution, or normal distribution, which one is more suitable to this dataset？ Thank you very much. Best,

Glad to help, I think what you are looking for is actually ordinal regression, see eg Estimating Monotonic Effects with brms and some discussion in make ordinal regression great again · Discussion #5066 · pymc-devs/pymc · GitHub You can see some more example in Rethinking chapter 11 ( resources/Chp_…

Fit mult-option data with Multinomial distributuion or normal distribution?

Questions

aetius January 12, 2022, 5:44pm 5

Thank you very much. Really appreciate it, it indeed solves my problem!

Topic		Replies	Views
How to model Normally distributed but integer data? Questions	3	689	December 30, 2019
Multi-Modal normal distribution Questions	1	1111	March 5, 2019
[quick conceptual question] shouldn't the lognormal distribution be used as the likelihood more often? Questions	5	1209	August 6, 2019
How to model observed percentages (bounded from 0 to 1) Questions	8	2801	January 3, 2018
Inferring expectation value of complicated distribution Questions	1	1040	November 1, 2017

Fit mult-option data with Multinomial distributuion or normal distribution?

Related topics