I think at that point you may as well skip the test and just make the change you... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		scott_w 6 months ago \| parent \| context \| favorite \| on: P-Hacking in Startups I think at that point you may as well skip the test and just make the change you clearly want to make!

bigfudge 6 months ago [–]

Or collect some data and see if the net effect is positive. It’s possibly worth collecting some data though to rule out negative effects?

scott_w 6 months ago | [–]

Absolutely, you can still analyse the outcomes and try to draw conclusions. This is true even for A/B testing.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact