Hacker News new | ask | show | jobs
by AznHisoka 2784 days ago
is a survey of 6000 adults really significant enough? I'm not an expert in statistics, but that seems awfully low.
1 comments

6000 is absolutely fine if it's a random sample of the adult population (it would be accurate to within 1%). An important thing to know is that the size of the US population doesn't affect this number.

It's much more likely that the survey has other flaws that prevented it getting a representative sample of US adults than that it got weird answers because the sample size was too small.