probml / pml-book

"Probabilistic Machine Learning" - a book series by Kevin Murphy

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

tweaks to sec 5.5 (frequentist hypothesis testing)

murphyk opened this issue · comments

In sec 5.5.2-5.5.3, I clarified the fact for the NHST approach (based on p-values), you only need to specify H0, and do not need a fully specified alternative hypothesis, unlike the case when working with Neyman-Pearson (decision theoretic approach).