Double Machine Learning with Gradient Boosting and its Application to the Big N Audit Quality Effect

35 Pages Posted: 13 Mar 2019 Last revised: 30 Jul 2019

See all articles by Jui-Chung Yang

Jui-Chung Yang

Department of Economics, National Tsing Hua University

Hui-Ching Chuang

Yuan Ze University - College of Management

Chung-Ming Kuan

Department of Finance, National Taiwan University

Date Written: July 28, 2019

Abstract

In this paper, we study the double machine learning (DML) approach of Chernozhukovet al. (2018) for estimating average treatment effect and apply this approach to examine the Big N audit quality effect in the accounting literature. This approach relies on machine learning methods and is suitable when a high dimensional nuisance function with many covariates is present in the model. This approach does not suffer from the“regularization bias” when a learning method with a proper convergence rate is used.We demonstrate by simulations that, for the DML approach, the gradient boosting method is fairly robust and to be preferred to other methods, such as regression tree,random forest, support vector regression machine, and the conventional Nadaraya-Watson nonparametric estimator. We then apply the DML approach with gradient boosting to estimate the Big N effect. We find that Big N auditors have a positive effect on audit quality and that this effect is not only statistically significant but also economically important. We further show that, in contrast to the results of propensity score matching, our estimates of said effect are quite robust to the hyper-parameters in the gradient boosting algorithm

Keywords: Audit Quality, Average Treatment Effect, Big N Effect, Double Machine Learning, Gradient Boosting, Performance-Matched Discretionary Accruals

JEL Classification: C14, C31, M42

Suggested Citation

Yang, Jui-Chung and Chuang, Hui-Ching and Kuan, Chung-Ming, Double Machine Learning with Gradient Boosting and its Application to the Big N Audit Quality Effect (July 28, 2019). USC-INET Research Paper No. 19-05. Available at SSRN: https://ssrn.com/abstract= or http://dx.doi.org/10.2139/ssrn.3351314

Jui-Chung Yang (Contact Author)

Department of Economics, National Tsing Hua University ( email )

101, Sec. 2, Kuang-Fu Road
HsinChu, 30013
Taiwan

HOME PAGE: http://https://sites.google.com/site/juichungyang/

Hui-Ching Chuang

Yuan Ze University - College of Management ( email )

135, Yuan-Tung Rd.
Taoyuan, 320
Taiwan
886-972-735-021 (Phone)

Chung-Ming Kuan

Department of Finance, National Taiwan University ( email )

1, Sec. 4, Roosevelt Road
Taipei, 106
Taiwan
886 2 3366-9541 (Phone)

HOME PAGE: http://homepage.ntu.edu.tw/~ckuan

Register to save articles to
your library

Register

Paper statistics

Downloads
138
Abstract Views
1,009
rank
281,081
PlumX Metrics