Count (and count-like) data in finance

• 成果类型: Article
• 署名作者: Cohn, Jonathan B.; Liu, Zack; Wardlaw, Malcolm I.
• 署名单位: University of Texas System; University of Texas Austin; University of Houston System; University of Houston; University System of Georgia; University of Georgia
• 刊物名称: JOURNAL OF FINANCIAL ECONOMICS
• ISSN/ISSBN: 0304-405X
• DOI: 10.1016/j.jfineco.2022.08.004
• 发表日期: 2022
• 页码: 529-551
• 关键词: Empirical methods; count data; Poisson regression

摘要

This paper assesses different econometric approaches to working with count-based out-come variables and other outcomes with similar distributions, which are increasingly com-mon in corporate finance applications. We demonstrate that the common practice of es-timating linear regressions of the log of 1 plus the outcome produces estimates with no natural interpretation that can have the wrong sign in expectation. In contrast, a simple fixed-effects Poisson model produces consistent and reasonably efficient estimates under more general conditions than commonly assumed. We also show through replication of existing papers that economic conclusions can be highly sensitive to the regression model employed.(c) 2022 Elsevier B.V. All rights reserved.