Hacker News Reader

Maybe you should reconsider. Sampling over people around you is a lot more accurate metric than global statistics.

First you have data sample that is relevant to people just like you. That means that you do not have to compensate for other factors as you're affected in the same way.

Second you do not have to trust other people for properly gathering, processing, and presenting the data.

View on HN

All well and good, but your sample is usually very small and you as a human being can't handle confounding factors very well. Add on the fact that you are also prone to selection bias...

That's the point! Selection bias compensates for all your confounding factors. You're in the same bin as your friends. Same factors, same outcomes.

For example how many of your friends (or friends of friends if your sample is too small) are dead in auto accidents is a lot better predictor for your fate than any global country statistics you can find.

Er rather, I meant a different selection bias. The one where you selectively remember friends that fit your hypothesis.

Also, the thing with quite a few statistics is that the risk is say 1/1000, and I honestly have closer to 50 people who I interact with in a month.

Reply on news.ycombinator.com