运用双尺度分布最近邻估计对公司盈利能力作异质性因果推断

doi:10.3969/j.issn.0253-2778.2020.12.006

中国科学技术大学学报 ›› 2020, Vol. 50 ›› Issue (12): 1488-1497.DOI: 10.3969/j.issn.0253-2778.2020.12.006

运用双尺度分布最近邻估计对公司盈利能力作异质性因果推断

1. 中国科学技术大学管理学院,安徽合肥230026; 2. 中央财经大学保险学院,北京100081

收稿日期:2020-09-09 接受日期:2020-12-17 出版日期:2020-12-30 发布日期:2021-03-04
基金资助:

Heterogeneous causal inference of corporate profitability using two-scale distributional nearest neighbor estimation

1. School of Management, University of Science and Technology of China, Hefei 230026; 2. School of Insurance, Central University of Finance and Economics, Beijing 100081

Received:2020-09-09 Accepted:2020-12-17 Online:2020-12-30 Published:2021-03-04
Contact: Zheng Zemin ( corresponding author) is Full Professor at the department of management, University of Science and Technology of China. He received his B. S. degree from USTC in 2010 and Ph. D. degree from University of Southern California in 2015. Afterwards, he was working in Department of Management, University of Science and Technology of China. His research interests include high dimensional statistical inference and big data problems. Wu Jie (corresponding author) is currently a Ph. D. student from School of Management, University of Science and Technology of China. She received her B. S. degree from Anhui University of Technology in 2017. Her research mainly focuses on high dimensional variable selection, classification.
About author:He Yu and Wu Yue are co-first authors. He Yu is a graduate student under the supervision of Prof. Zheng Zemin at University of Science and Technology of China (USTC). Her current research is mainly focused on statistical inference and applications. Wu Yue received her Ph. D. degree from State University of New York. She is currently an associate professor at Central University of Finance and Economics. Her research interests cover risk management, dynamic optimization and insurance.
Supported by:
This work was supported by National Natural Science Foundation of China (72071187, 11901603, 11671374, 71731010, and 71921001), and Fundamental Research Funds for the Central Universities (WK347000 0017 and WK2040000027).

摘要/Abstract

摘要：

异质性治疗效应是现代因果推断的一个重要内容,在金融领域也有非常广泛的应用.研究提高偿债水平对不同营运能力的上市公司盈利能力的异质性效应,以消除上市公司个体差异带来的影响,使得估计结果更加准确.在估计方法的选择上,选择了双尺度分布最近邻估计.它能够消除估计中的一阶有限样本偏差,并且它在正则化条件下是渐近无偏和渐近正态的.因此,应用双尺度分布最近邻估计对CSMAR中国上市公司财务报表数据库中的中国上市公司财务指标进行了实证分析,研究了不同经营能力下公司的偿债能力提高对于公司盈利能力是否存在异质性治疗效应.根据其研究结果,对优化上市公司财务结构,提高上市公司的盈利能力给出了相应的建议.

关键词: 异质性治疗效应, 双尺度分布最近邻, 营运能力, 盈利能力, 偿债水平

Abstract:

The heterogeneous treatment effect is the center of gravity in modern causal inference and is also widely used in the financial field. Studying the heterogeneous effect of improving solvency on the profitability of listed companies with different operational capabilities can eliminate the impact of individual differences in listed companies and make the estimation results more accurate. The two-scale distributional nearest neighbor (DNN) is able to eliminate the first-order finite sample bias in the estimate, and it is asymptotically unbiased and asymptotically normal under regularization conditions. Therefore, an empirical analysis was conducted of the financial indicators of Chinese listed companies in the CSMAR financial statement database by using the two-scale distributional nearest neighbor estimation. And a study was carried out on that whether there is heterogeneity in the impact of corporate solvency reduction on corporate profitability under different operating capabilities. Corresponding suggestions were given for optimizing the financial structure and improving the profitability of listed companies.

Key words: heterogeneous treatment effects, two-scale DNN, operating ability, profitability, solvency

中图分类号:

F830

何雨, 吴越, 郑泽敏∗, 吴捷∗ . 运用双尺度分布最近邻估计对公司盈利能力作异质性因果推断 [J]. 中国科学技术大学学报, 2020, 50(12): 1488-1497.

HE Yu , WU Yue , ZHENG Zemin∗, WU Jie∗ . Heterogeneous causal inference of corporate profitability using two-scale distributional nearest neighbor estimation [J]. Journal of University of Science and Technology of China, 2020, 50(12): 1488-1497.

[1]	张萍, 王雅实, 吴钦宇. 应用CoGVaR方法度量系统风险贡献[J]. 中国科学技术大学学报, 2021, 51(6): 475-484.
[2]	黎明, 温灿红. 通过稀疏PCA分析新冠疫情对股市的影响[J]. 中国科学技术大学学报, 2021, 51(5): 404-418.
[3]	孟徐然，毕秀春，张曙光. 基于生成对抗网络的高频算法及其回测研究[J]. 中国科学技术大学学报, 2020, 50(6): 801-810.
[4]	张志远，叶五一. 基于MIDAS-Expectile回归模型的加密货币风险测度[J]. 中国科学技术大学学报, 2020, 50(6): 860-872.
[5]	叶五一，丁雅霖，焦守坤. 基于TV-Copula-X模型的金砖国家股指收益率与波动率的动态相依关系[J]. 中国科学技术大学学报, 2020, 50(5): 612-628.
[6]	郑祥，韦勇凤. 基于Merton模型与Monte Carlo模拟的障碍期权定价对冲[J]. 中国科学技术大学学报, 2018, 48(11): 906-922.
[7]	孙达昌，毕秀春. 基于深度学习算法的高频交易策略及其盈利能力[J]. 中国科学技术大学学报, 2018, 48(11): 923-932.
[8]	龙奥明，毕秀春，张曙光. 基于LSTM神经网络的黑色金属期货套利策略模型[J]. 中国科学技术大学学报, 2018, 48(2): 125-132.
[9]	刘刚, 崔振嵛, 刘彦初, 谢金贵. Lévy过程下金融期权风险对冲参数的模拟仿真估计[J]. 中国科学技术大学学报, 2017, 47(3): 262-266.
[10]	蔡嫱，李勇. 汇率波动对资本市场间溢出效应的影响[J]. 中国科学技术大学学报, 2016, 46(12): 1036-1040.
[11]	罗克兵，叶五一，董筱雯. 高频连涨连跌收益率的分位点Granger 因果检验与条件VaR估计[J]. 中国科学技术大学学报, 2016, 46(11): 919-927.
[12]	王传好，方兆本，韩宇. 基于多分辨率分析和极值理论的集合VaR模型[J]. 中国科学技术大学学报, 2016, 46(11): 928-938.
[13]	杜宇能，杜敏. 我国证券市场宏观政策信息与市场有效性的联动关系[J]. 中国科学技术大学学报, 2016, 46(8): 696-701.
[14]	张勔, 程希骏, 方正, 郭键鸿, 刘峰. 基于pair copula-LMSV-t模型的投资组合风险研究[J]. 中国科学技术大学学报, 2015, 45(12): 1024-1029.
[15]	朱业春, 曹崇延. 基于熵补偿的Black-Litterman模型的投资组合[J]. 中国科学技术大学学报, 2015, 45(12): 1030-1035.

运用双尺度分布最近邻估计对公司盈利能力作异质性因果推断

Heterogeneous causal inference of corporate profitability using two-scale distributional nearest neighbor estimation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价