Data Truncation Bias, Loss Firms, and Accounting Anomalies

• 成果类型: Article
• 署名作者: Teoh, Siew Hong; Zhang, Yinglei
• 署名单位: University of California System; University of California Irvine; Chinese University of Hong Kong
• 刊物名称: ACCOUNTING REVIEW
• ISSN/ISSBN: 0001-4826
• DOI: 10.2308/accr-10032
• 发表日期: 2011
• 页码: 1445-1475
• 关键词: cross-sectional variation; earnings management; Cash flows; accruals; persistence; performance; INFORMATION; disclosure; returns

摘要

Ex post trimming of extreme returns observations that are not data errors causes spurious inferences in tests of market efficiency and behavioral explanations for anomalies. Trimming causes a downward truncation bias in estimated mean returns that is stronger in ex ante subsamples with more loss firms and in which return distributions are more right-skewed. There is an asymmetric U-shaped relation between return right-skewness and loss frequency across deciles of negative return predictors (Accruals, Delta NOA, and NOA), and a downward sloping relationship for positive return predictors (CFO and FCF). Consequently, a least-trimmed square (LTS) 1 percent deletion of returns induces a spurious inverted-U-shaped relation between returns and negative predictors, and an exaggerated positive relation for positive predictors. Thus, the resulting trimmed relations do not reject behavioral explanations for these anomalies. Trimming also induces a spurious loss anomaly. These findings highlight that in return prediction studies, observations should not be deleted based upon the values of the dependent variable, only based upon clearly identified data errors.