Does anyone familiar with the induction process in section 4.5.1？

[linsanityyong]

I‘m confused with the derived form of the score on the whole data. If the author trys to use hypergeometric distribution to characterize the process, i think the score should be just like N*k/n, provided N is size of the whole data, n is size of the subset, k is the number of score on subset. Does anyone know the source of formula (8) and (9)?

By the way, is there anyone use another programming language(python or matlab) to reproduce this code? I hope we can share and talk about some details.