Kind vs Wicked

[timelets]

Rather than assuming that both situations (e.g., past and present) are random samples from the same underlying population, we posit two distinct settings. We refer to the first as L (for learning) and the second as T (for target) and ask how these match.

DOI: 10.1177/0963721415591878

Comments

[malobukov]

It's trivial to do better than random on physical appearance, so calling it unrelated is a stretch.

[timelets]

Sorry, I don't quite get your point. Can you elaborate on it a little bit.

[malobukov]

For example, shoe size is correlated with ability to solve math problems. Majority of good programmers wear trousers. Obese people can't perform well in physically demanding jobs. People with grey hair tend to have more experience.

Those correlations may not be strong, but they are not zero either.

[timelets]

Got it. Thanks.