An introduction to rejection sampling
Вставка
- Опубліковано 14 тра 2018
- Explains how to independently sample from a distribution using rejection sampling.
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.uk/Students-Gui...
For more information on all things Bayesian, have a look at: ben-lambert.com/bayesian/. The playlist for the lecture course is here: • A Student's Guide to B...
Every time when I have statistics problems and nobody could help me, I could always find answers in your videos! Really helpful and intuitive! Thank you so much!
Hi Ben, Thank you very much for the video! I learned it in class but didn't understand it. You saved my Homework and Midterm!
When I google a concept and a Ben Lambert video pops up all my worries fade away.
Thank you so much for this! I read about this topic on Gelman, and did not understand what it was, but this helped soooo much :)
Hi Ben, thanks for making this useful video. The presentation with Shiny animation results looks great.
Thank you for the excellent video.
Fantastic explanation!
Hi Ben, what is options3 for you in your mathematica notebook? Great explanation by the way!
Really nice and practically explained
Clear explanation!
Thanks so much!
thanks!!!
In this case we already knew the posterior to be exponential. What if we dont know the posterior?
Nice explanation.
so is rejection sampling more useful if we don't know the pdf of the r.v. we are dealing with (if we only know the shape I assume?), and not very useful the other way around?
2:25 isn't the curve p(x), not the y-axis?
Fantastic explanation, thanks a lot, my lecturer was making it look like rocket science lol
If you want to generate from 0 to infinity you just have to turn the 8 sideways
Nice video
How did you get (generate) the exponential line?
he plotted the function appearently
I don't understand what we can do with this? what is the point?
Integrate any function from which we cannot sample directly, which will usually be the case in a bayesian context (e.g. hierarchical models)
Monte Carlo integration with importance sampling.
MVP