How long must a firm be great to rule out chance? Benchmarking sustained superior performance without being fooled by randomness

Abstract

AbstractAlthough sustained superior firm performance may arise from skillful management or other valuable, rare, and inimitable resources, it can also result from randomness. Studying U.S. companies from 1965–2008, we benchmark how long a firm must perform at a high level to be confident that it is something other than the outcome of a time‐homogeneous stationary Markov chain defined on the state space of percentiles. We find (a) the number of sustained superior performers in Compustat, measured by ROA and Tobin's q, exceeds the number of false positives we would expect to be generated by such a process; yet (b) the occurrence of false positives is often enough to fool many observers, so (c) the identification of sustained superior performers requires particularly stringent benchmarks to enable valid study. Copyright © 2011 John Wiley & Sons, Ltd.