Tag: human

Posted on

Guess the Correlation!

Here’s a fantastic way to kill a few minutes better understand correlation coefficients: http://guessthecorrelation.com/

You’re shown a simple scatter plot and enter the correlation coefficient you guess to be associated with it. If you’re close enough, you get coins, if you’re too far off, you lose a heart. There’s even a two-player mode. Basic gaming stuff, but you also build an intuition of what those correlation coefficients we’re throwing around all the time actually mean.

There’s more, though. The game also serves (another) serious purpose: Omar Wagih is collecting the data to analyse how we mortals perceive correlations in scatter plots.

Posted on

Should I review this?

I have just received an invitation to review an article by a publisher that’s — let’s say “less established”. Given that they have been accused of being a predatory publisher in the past, I was at first positively surprised: There was none of this silly flattering of being a leading expert etc. and they apparently did try to get a proper review. Then came the title and the abstract. It had “public attitudes” in it, and a “scoping review” — so if you allow for synonyms in the keyword search, I can see how their machine picked me, but if no human is involved, neither am I (irrespective of the fact that this was utterly out of my expertise). Maybe we should react with automatized reviews, a fork of SciGen perhaps?