Inefficiency in Earnings Forecasts: Experimental Evidence of Reactions to Positive vs. Negative Information

Abstract

Prior archival studies of analysts' forecasts have found evidence for systematic underreaction, systematic overreaction, and systematic optimism bias. Easterwood and Nutt (1999) attempt to reconcile the conflicting evidence by testing the robustness of Abarbanell and Bernard's (1992) underreaction results to the nature of the information. Consistent with systematic optimism, forecasts are found to underreact to negative earnings information but overreact to positive information. However, Easterwood and Nutt are unable to distinguish between misreaction caused by incentives unique to analysts with misreaction caused by human decision bias that may be typical of investors. We address this issue by analyzing forecast reactions to positive versus negative information in the controlled experimental setting of Gillette, Stevens, Watts, and Williams (1999). This experimental setting has the potential to detect human decision bias because it is void of potentially confounding incentives of analysts, contains a simple forecasting objective (a random-walk series), and provides learning opportunities and economic incentives to minimize forecast error. We find a systematic forecast underreaction to both positive and negative information, and the underreaction is generally greater for positive information than negative information. These results suggest that prior empirical evidence of forecast overreaction to positive information is unlikely to be attributable to human decision bias.

Keywords: earnings forecasts, controlled experiments, human decision biases

JEL Classification: D46, D84, G29, M41