These notes are too pedagogical to be published, but I wrote them up while starting new projects. Please let me know if you find any typos or errors!

Back to main page.

Collected notes and projects on statistics and learning

Various notes and projects related to statistics and learning algorithms, as I slowly learn this large and rapidly evolving field. None of this has gone through a rigorous editing or peer review process. I am posting this here as I've learned much from other people's notes and blogs on statistics, so perhaps these will be useful to someone. If anything is unclear, if you find any mistakes, or if you have any suggestions for improvement, please let me know. The repository for the paper is here.

Notes on parametric Bayesian statistics

Notebooks on Markov chain Monte Carlo (MCMC) methods

My solutions (in the form of Pluto notebooks) to a set of instructive MCMC problems originally posed by Neil Cornish. There are many high quality packages to perform MCMC sampling; these notes/solutions are just for pedagogical use! These notebooks may contain errors. Please let me know if you spot any, or if you would like to improve these solutions in any way. The source code for these notebooks can be found here.

Assignment 1: Metropolis Hastings algorithm to sample from a distribution

Assignment 2: Determining the posterior probability for model parameters

Assignment 3: Langevin MCMC and parallel tempering