Richard McElreath in his book Statistical Rethinking Chapter 13 models varying intercepts where categories covary not in a discrete way but based on a continuous variable. In his example he uses euclidean distance as the metric of similarity between data generating points. He then uses this kernel …

Actually, in his book, Osvaldo Martin ported McElreath’s islands example to PyMC3 using the pm.gp class . I don’t know if it answers your questions, but it might give you some pointers.

Gaussian Process used to model varying intercepts in GLM

Questions

Mind-The-Data October 4, 2019, 8:31pm 6

Here is a kruschke diagram of the model I am trying to reparameterize:

Topic		Replies	Views
Gaussian Process Regression-- reparameterizing to us pm.gp class Questions	2	505	October 3, 2019
Sparse GP with linear covariate? Questions	2	613	August 3, 2021
Multiple (uncertain) function observations of the same Gaussian process Questions	15	6568	October 16, 2017
Extending Gaussian Process functionality: Coregion and beyond Development	19	2390	November 25, 2017
Multidimensional Sparse GP Questions theano	9	847	April 9, 2021

Gaussian Process used to model varying intercepts in GLM

Related topics