The importance of step size for Random Walk Metropolis

This video illustrates the importance of choosing appropriate step sizes for each of the parameters in random walk Metropolis. In particular, I focus on how choosing a step size that is too small or large results in slow convergence to the posterior.
This video is part of a lecture course which closely follows the material covered in the book, "A Student's Guide to Bayesian Statistics", published by Sage, which is available to order on Amazon here: www.amazon.co....
For more information on all things Bayesian, have a look at: ben-lambert.co.... The playlist for the lecture course is here: • A Student's Guide to B...

[@Stefan-bs3gm]

Hi Ben, I love this video series and your book. I am experimenting with MC algorithm visualizations myself a little bit and I am wondering how you reconstruct the function surfaces from the samples. Are you using some kind of gaussian kernel with variance depending on the number of samples? Would love some more information / references on this!
Cheers

[@yanli9126]

very nice video, thank you