Simpsons paradox and mixed models - large number of groups

@cluhmann thanks for clarifying. I think I roughly see what your getting at but I defiitively need to sit down and write it out in order to develop a thorough understanding.

Your explanations are incredibly helpful, thanks a lot for your time.

If there are any suggestions on how to improve the low ESS I am observing then I’d be glad to look into that.

I am learning a lot here and the available pymc examples are terrific.

2 Likes