Regression Fallacy

Questions

What is Regression Fallacy?

The Regression Fallacy is the error of assuming an unusually high or low result will continue, or of crediting some action when results drift back toward average. Extreme outcomes usually contain a large dose of luck, and luck rarely repeats on cue.

How do you avoid Regression Fallacy?

Before rewarding, punishing or changing course after a dramatic swing, look at a longer track record. Ask whether you are seeing a new level or just a temporary peak or trough. Judge people, investments and remedies by patterns, not single moments.

When does Regression Fallacy matter?

Regression Fallacy is one of the 68 mental models for evidence, the situations where you ask: Is this really true? Within that, it belongs to “Cause or coincidence?”, alongside Causal Fallacy, Clustering Illusion and Confounding Factor.

What is an example of Regression Fallacy?

Two stories show it at work: The cover jinx (1954) and Morningstar stars (2017). Both are told in full in The Mental Models Daily Almanac, which has two stories for each of its 365 models.

Which mental models are related to Regression Fallacy?

Regression to the Mean, Hindsight Bias and Halo Effect. Regression Fallacy itself comes from general thinking.