Because of upward trends in research and development activity, accounting measures of financial distress have become less accurate. We document that (1) higher research and development spending increases the likelihood of misclassifying solvent firms, (2) adjusting for conservative accounting of research and development increases the number of correctly identified distressed firms, and (3) adjusted measures of distress alleviate previously documented anomalously low returns of large, high distress risk, low book‐to‐market firms. The results hold after updating stale parameters and under various tax assumptions. Our evidence raises concerns about interpretation of extant literature that relies on accounting measures of distress.

Even though stock returns are not highly autocorrelated, there is a spurious regression bias in predictive regressions for stock returns related to the classic studies of Yule (1926) and Granger and Newbold (1974) . Data mining for predictor variables interacts with spurious regression bias. The two effects reinforce each other, because more highly persistent series are more likely to be found significant in the search for predictor variables. Our simulations suggest that many of the regressions in the literature, based on individual predictor variables, may be spurious.