Evidence on the Superiority of Analysts Quarterly Earnings Forecasts for Small Capitalization Firms*
研究发现，分析师对小公司的季度每股盈利预测比大公司更准确，且时间序列模型参数对分析师覆盖的小公司预测精度有信息含量。
Financial analysts provide information to support investment analysis and decisions for an ever increasing number of firms. As part of their services they also produce earnings forecasts for covered firms. While there has been much research investigating the determinants of financial analyst earnings forecast superiority for large, widely‐followed firms, little research has focused on smaller firms. Until recently, these smaller firms have been largely ignored. This study focuses exclusively on small firms and provides evidence of differing behavior for such firms compared to results previously reported for large firms. Errors in quarterly earnings per share forecasts of small firms obtained from a univariate time‐series model are also examined. Regression results indicate that time‐series model parameters possess information content with respect to forecast accuracy for analyst‐covered firms only. These results are obtained after controlling for firm size, model adequacy, and industry, quarter, and year effects. This suggests that analysts are more likely to cover small firms for which they are able to decipher information correlated with that impounded in the “shocks” in the quarterly earnings time series as captured by the time‐series model parameters.