The answer to question #6 of chapter 13 seems wrong.

[danli349]

Hello:

I think the answer to question #6 (c,d) of chapter 13 (https://danhalligan.github.io/ISLRv2-solutions/multiple-testing.html) is wrong.
The FDP is defined with V/(V+S), which is (false positive)/(false positive+true positive),
For Bonferroni procedure the false discovery rate will be 0/7, 0/7, 0/3.
For Holm procedure the false discovery rate will be 0/7, 0/8, 0/8.

[danhalligan]

Agreed -- this looks like an error thanks. Do you want to make a pull request and I'll merge in? If not, I can make the edits.

[danli349]

@danhalligan you can make the edits, thanks