Hacker News Reader

Comment by jawns | Hacker News Reader

This is the reason why I don't include P values on http://www.correlated.org.

They would muddle my otherwise irreproachable statistics.

I bet the p-values on that site would be very high if properly calculated. Generally, if you are reporting correlations between a large number of variables, the p-values shoot through the roof.

Of course, TONS of people forget this and publish a p-value as if those two variables are the only ones under consideration. Which is just sad.

With correlation statistics the p value is proportional to the sample size.

I think we're talking about different experiments. I'm not talking about, "here are the correlation statistics for 100 variables", I'm talking about, "I tested 100 variables, and these are the five pairs which are most strongly correlated."

At which point you need to do some variant on principal components analysis on the covariance matrix.

Holy crap this site is fantastic. Thanks.

Woah, why didn't I know about this site? Awesome! Would be great if you'd include links to you original sources. Even though you don't include P-values in the graphics, on the detail page I would still love them just as much as Chi-square. Your tagline should be "correlation does not imply causation" ;-)

The original source is the site itself. Every day, a new poll question is posted. That poll-question data is used to form new correlations.

Ah!

Reply on news.ycombinator.com