Hacker News new | ask | show | jobs
by political12345 1375 days ago
> Highly correlated" would not be the choice of words I use to describe correlations between (0.23 - 0.5).

lol, this range is 0.5 to 0.7 variance explained (R squared) which is an insane value. in typical social studies a correlation of > 5% is considered a major improvement. In finance a correlation or > 1% is considered amazing.

You are either a hyper-intelectual drinking Taleb's kool-aid or simply don't know what you are talking about :D

2 comments

If the correlation is 0.2 then it explains 4% of the variance. If it's 0.5, then 25%. I'm not sure how you got your numbers, can you clarify?

Also 10% variance explained in social science is considered pretty good (which is depressing, but such is life).

> a hyper-intelectual

Very far from it. I'm just an idiot with Internet access.

> drinking Taleb's kool-aid

I do agree with some of what he has said about IQ, but I am not well-versed in any of his other writings.

> simply don't know what you are talking about

Perhaps, but I am still not convinced.