Assorted Links

Thanks to Patrick Vlaskovits.

3 Replies to “Assorted Links”

  1. “When it’s extremely low cost to perform inference, you are likely to perform a lot of inferences. When your first regression gives a non-result, you run a second one, and a third one, etc. This leads untrained researchers to run into multiple comparisons problems and increases the risk of Type I errors.” But it also enormously improves the chances of finding something publishable.

    Seth: “Untrained researchers”– ha ha! It’s better to find something than nothing even if you can’t put a p value on the something. In the early days of exploratory data analysis respected statisticians criticized it because they said it would lead to finding patterns where no patterns existed.

Comments are closed.