I’ve been a bit negligent in sharing my recent writing with the forums.
Sampling and the Monte Carlo Method
What exactly are samples in theory and in practice? How do we use them for probabilistic computation?
A review of how heavy-tailed hierarchical models can be used to induce sparsity in inferences, both in theory and in practice.
Narratively Generative Modeling
The term “generative modeling” is a bit abused these days; in this piece I discuss how a focus on probabilistic story telling can facilitate the construction of principled models compatible with meaningful domain expertise.
Practical techniques for developing principled prior models over one-dimensional spaces and multivariate spaces. Includes discussion of common heuristics that can fail in subtle and dangerous ways.
Stochastic Differential Equation Modeling
A very brief introduction to implementing stochastic differential equation models in Stan.
An exploration of things “regression” from a probabilistic modeling perspective with a strong focus on the strong, and often violated, assumptions implicitly made in “regression” models.
A few more a queued up for public release within the next month – first an introduction to survival modeling and then a discussion of some avant garde density functions for prior modeling.
All of my publicly-available case studies covering probability theory, modeling and inference, and modeling techniques are available on my writing page. They are also presented there in the recommended reader order.
If you find this useful and/or are interested is supporting more work consider supporting me on Patreon.