Regression to the mean
Why do unusually strong or weak market weeks tend to be followed by more ordinary ones?
In plain words
Regression to the mean is the tendency for an extreme result to be followed by a result closer to the market's usual level. It is not a law; it reflects that extreme weeks often contain forces that do not repeat.
Why it matters
Traders who size positions or extrapolate trends after an extreme week can carry expectations that the next week rarely meets. It matters for expectations, not for prediction: a market can stay extreme for several weeks before settling back.
In a real week: BTC, week of 26 June 2023
In the week of 26 June 2023, BTC rose 0.51%, a return ranked at the 48.0 percentile of 280 weeks of history, almost exactly the middle of its own record. The week before it had returned 15.65%, an extreme, and the three weeks before that returned 1.6%, -4.39% and -3.38%. After the outlier, the market's result returned to its ordinary middle.
A common mistake
Treating regression to the mean as a forecast that the next week will be flat. It describes a statistical tendency across many cases, not a rule for any single week.