The standard way to estimate the an expected value of a population from a sample of values
vn is to compute the average
(1/n) sumi = 1...n. It is well known in statistics that for grouped data, there are other estimators that can have smaller expected square error.
In this note on partial pooling in my “data for engineers” series I work examples in Python deriving and using the technique. I find the whole idea pretty exciting, so please check it out.
Categories: Expository Writing Pragmatic Data Science Statistics To English Translation Tutorials