What is regression toward the mean?

• A. The tendency for extreme scores to move toward the average on retesting
• B. A systematic error due to non-random sampling
• C. The increase in mean due to treatment effect
• D. The variation of means across groups due to sampling error

Answer: (A)

Regression toward the mean describes the tendency for extreme scores to move closer to the average on a subsequent measurement, mainly because a portion of an extreme result often comes from random fluctuation rather than true ability. When you measure something, the observed score combines the true value with random error. If someone scores very high (or very low) on one occasion, that extreme result likely included a larger-than-usual random error. On retesting, the random error component tends to cancel out, nudging the score back toward the overall mean. This is why extreme performances are often followed by more average ones.

So the statement that extreme scores tend to move toward the average on retesting best captures the idea. It’s not about systematic sampling bias, a treatment effect increasing the mean, or variation in group means due to sampling error; those describe different concepts.