Hi Y’all!
Is there an intuitive ELI5 guide that helps one determine which prior and likelihood function should be used based on your problem?
I’m not sure a 5 year old could understand it, but this document by the Stan team is really great for how to choose priors.
Likelihoods are more going to be driven by the nature of your data. Is it count data → Poisson. Is it binary → Bernoulli. Do you have a best guess that you know isn’t perfect → Normal, etc. It’s harder to give general advice on this front, since it’s really deeply tied to your specific model/data/research question.
3 Likes
Ben Lambert has a pretty neat tool which allows you to visualise probability distributions and gives practical tips for what they could be used for in different scenarios. I would definitely recommend his book too, he has some nice flow/decision charts on the right likelihood
4 Likes