Statistical Computation, MCMC and Bayesian Statistics
Hi all,
What you’ll learn
- Apply MCMC to Statistical Modeling.
- Greater understanding of statistical methods for simulation.
- How to write code in R or Python.
- How to perform nonparametric bootstrap.
- Apply optimization techniques to solve numerical and combinatorial problems.
- At the end of this course you will learn how to apply Monte Carlo methods to Bayesian problems for data analysis.
- Build genetic algorithms.
Course Content
- Introduction –> 5 lectures • 39min.
- Generating Random Variables –> 4 lectures • 32min.
- Monte Carlo Integration –> 4 lectures • 28min.
- Variance Estimation and Acceleration –> 5 lectures • 31min.
- Optimization –> 5 lectures • 1hr 13min.
- Expectation Maximization –> 2 lectures • 20min.
- MCMC and Metropolis Hastings –> 4 lectures • 45min.
- Gibbs Samplers –> 2 lectures • 19min.
Requirements
Hi all,
As of June, 2022, I have to let you know that this course is out of date. I am busy with life and will not be able to respond to any messages or questions. The content was written when I was applying to grad schools in 2018 so it’s a little rough, but the material will help anyone in their MS statistics/cs/economics programs. I unfortunately cannot change the pricing to free due to Udemy’s policies, but I hope this provides people with some basic understanding of Monte Carlo methods and statistical computing.
Best wishes,
Jonathan
——————-
This is a fully developed graduate-level course on Monte Carlo methods open to the public. I simplify much of the work created leaders in the field like Christian Robert and George Casella into easy to digest lectures with examples.
The target audience is anyone with a background in programming and statistics with a specific interest in Bayesian computation.
In this course, students tackle problems of generating random samples from target distributions through transformation methods and Markov Chains, optimizing numerical and combinatorial problems (i.e. Traveling Salesman Problem) and Bayesian computation for data analysis.
In this course, students have the opportunity to develop Monte Carlo algorithms into code “by hand” without needing to use “black-box” 3rd party packages.