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

Why sample as opposed to looking at the whole population? The typical reason is, "because it's difficult to survey the entire population". But in this case I'd think that it'd be easy because I assume you have all the data.


They likely don't record the team composition, so this would require hand-labeling of any data points.

Do we know total applicants? I'd like to know what n produced a 5% sample.




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

Search: