David Robinson gave a great example of Bayesian empirical beta distribution update. is he
- found the previous distribution and
- used this until update ratings for each test.
This had a remarkable effect of weighted averages based on the amount of data present and the decrease in observations with low data closer to the average.
How to update grades for counts and regular . I assume that Gamma is used for calculations, and Gaussian is used for normal, but I would like to see examples of this in R, if anyone has it.
source
share