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

You may well be right that they got there out of bias; I've only glanced at this.

How'd this bias manifest in their choice of which studies to review? The 4/5 opposite that I mentioned points the other way. (Added: I wrote this before you added an example paper.)

Of course their main point is supposed to be about finding ways to counter this effect of engineering desired results within academic standards. I agree that's a real thing and part of a huge problem.



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

Search: