Statistics

I provide a simple example of a Dirichlet regression in PyMC. This form of generalized linear model is appropriate when modeling proportions of multiple groups, that is, when modeling a collection of positive values that must sum to a constant. Some common examples include ratios and percentages.

I experimented with different structures for multi-level and hierarchical splines in PyMC, including using a multivariate normal prior distribution over the spline parameters.

How to build a hierarchical model in PyMC3 with a mixture of centered and non-centered parameterizations to avoid the dreaded funnel degeneracies.

How to fit a spline using the Bayesian modeling framework PyMC3.

I present a breif take on Dr. Silge’s Uncanny X-Men analysis using Bayesian methods.

How to find the point where two histograms overlap.