Hacker News new | past | comments | ask | show | jobs | submit login

Try plinking around on a sample size calculator a bit, the results might be surprising. For example:

https://www.surveymonkey.com/mp/sample-size-calculator/

If you are ok with a 25% margin of error and a 95% confidence level, 16 people is good enough. You have to make sure there isn’t some skew in your population, but if your method of sampling the population produces a skew, adding people won’t really help there.




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

Search: