hard20 pts · first answer countsstatisticscausal-inference

Worst stores improved on their own

Head office picked the 10 worst-performing stores last quarter and sent them a coach. This quarter all 10 improved, so the coaching is called a success. What is the biggest flaw?

A.Ten stores is too many to coachB.Regression to the mean: stores chosen for an unusually bad quarter tend to move back toward average anyway, so you need a similar uncoached comparison groupC.Quarterly data is always too noisy to useD.The coach should have visited the best stores instead

← Halving the margin of error Correlation near zero →