Pages

Thursday, January 7, 2021

The Dunning–Kruger effect

The Dunning–Kruger effect is a favorite of pseudo-intellectual leftists. Wikipedia defines it as:
a cognitive bias in which people with low ability at a task overestimate their ability. It is related to the cognitive bias of illusory superiority and comes from people's inability to recognize their lack of ability. Without the self-awareness of metacognition, people cannot objectively evaluate their level of competence. ...

Colloquially, people experiencing this bias are said to be "on Mount Stupid".

It is used to mock people all the time, without addressing the substance of what they say, such as:
Mr. X says Y, but he doesn't realize that he lacks the competence to say that. It is an example of the Dunning-Kuger effect. Ha, ha. He probably doesn't even know what the Dunning-Kruger effect is. Ha, ha, ha. People with his opinions never do. Ha, ha.
It turns out that it is the jerks who cite Dunning-Kruger who are the dummies, as the effect is bogus. This article explains that it is just a data artifact.

Suppose you measure something in two different ways, each with some error. Simple statistical considerations tell us that the extremes of one measurement are not likely to be so extreme in the other measurement. That was the main thing that Dunning and Kruger found.

In particular, they found that when someone does very well on a test, he often does better than he expected. And when he does poorly, it is often worse than he expected. Using some innumerate mumbo-jumbo, they expressed this as a profound result, as defined above.

Apparently mathematicians and statisticians have been aware for years that the effect is bogus, and yet it continues to be cited by academics, psychologists, social commentators, and even the NY Times anyway.

I know what you are thinking: Aren't the people who cite the Dunning-Kruger effect good examples of the effect? Ha, ha.

There are still examples of cognitive biases, and here is a long list. But citing Dunning-Kruger in lieu of a substantive argument is just a sign of ignorance.

1 comment:

  1. Yes. All I would add is that where the burden of proof is on your opponent, and you feel they haven't carried it, under those circumstances you might want to mention D-K to them as a courtesy because such mention might usefully "unhorse them on high".

    If it's their burden, you don't want to do their work for them; and you may not even care to point them in a particular new direction. Instead, you're just trying to nudge them away from what seems like a belief that they're somehow infallible.

    ReplyDelete