Sampling Importance Resampling (SIR) скачать в хорошем качестве

Sampling Importance Resampling (SIR)

Become a member! https://meerkatstatistics.com/courses/ 🎉 Special YouTube 60% Discount on Yearly Plan – valid for the 1st 100 subscribers; Voucher code: First100 🎉 * Why become a member? All video content Extra material on complete-courses (notebooks) Access to code and notes Community Discussion No Ads Support the Creator ❤️ If you’re looking for statistical consultation, work on interesting projects, or training workshop, visit my website https://meerkatstatistics.com/ or contact me directly at david@meerkatstatistics.com ~~~~~ SUPPORT ~~~~~ Paypal me: https://paypal.me/MeerkatStatistics ~~~~~~~~~~~~~~~~~ While Importance Sampling (IR) allows you to calculate "quantities of interest" (e.g., normalizing constant, mean, etc.) of unnormalized ("hard") distributions (e.g., unnormalized posteriors), Sampling Importance Resampling (SIR) allows you to also obtain a sample from it, and also move your sample from one distribution to another quite easily (e.g. change in prior [aka sensitivity analysis]). [As a side note which isn't mentioned in the video, SIR can also improve the accuracy of Variational Inference (VI) - when you use a VI approximation as the proposal g, and then use SIR to get samples from the unnormalized posterior = joint: that sample can be more accurate than sampling directly from the VI distribution]