THE J-SHAPE OF PERFORMANCE PERSISTENCE GIVEN SURVIVORSHIP BIAS

Performance may enhance survival probability. When it does, the induce d lack of randomness challenges robust and unbiased inference. If surv ivors are sorted into two groups based on past performance, spurious p ersistence has been demonstrated if variance in performance is heterog eneous. However, as we show both theoretically and with simulations, i f performance is categorized finely, the spurious persistence will be J-shaped; that is, at the bottom better performance in one period ''pr edicts'' worse performance for another period. We propose a simple t-t est applied to the quadratic coefficient in a regression to distinguis h between a spurious J-shape and monotonic patterns. Mutual funds, our example, exhibit the monotonically increasing pattern produced by tru e performance persistence.