Modeling Conditional Distribution Discontinuities

54 Pages Posted: 14 Feb 2018 Last revised: 1 Aug 2018

See all articles by Dmitri Byzalov

Dmitri Byzalov

Temple University - Fox School of Business and Management - Department of Accounting

Sudipta Basu

Temple University - Department of Accounting

Date Written: July 30, 2018

Abstract

We develop new tests of distribution discontinuity conditional on multiple explanatory variables, which can be used to analyze meet-or-beat behavior around benchmarks. These tests combine Burgstahler and Dichev’s (1997) intuition on benchmark-driven earnings management with a flexible statistical model that addresses important limitations of the existing distribution discontinuity tests. Our conditional discontinuity method offers large improvements in test performance relative to both histogram-based tests of the existence of distribution discontinuity and logit-based tests of the determinants of distribution discontinuity, and it changes some of the major findings in the earnings discontinuity literature. Our method is flexible, robust, and easy to implement in standard statistical software. Future research in many fields could benefit by adopting our distribution discontinuity tests.

Keywords: standardized difference test; zero benchmark; smooth distribution; nonlinear interpolation; conditional distribution

JEL Classification: M41; C20; C25

Suggested Citation

Byzalov, Dmitri and Basu, Sudipta, Modeling Conditional Distribution Discontinuities (July 30, 2018). Fox School of Business Research Paper No. 18-009; AAA 2019 Management Accounting Section (MAS) Meeting. Available at SSRN: https://ssrn.com/abstract=3117088 or http://dx.doi.org/10.2139/ssrn.3117088

Dmitri Byzalov (Contact Author)

Temple University - Fox School of Business and Management - Department of Accounting ( email )

Philadelphia, PA 19122
United States

HOME PAGE: http://astro.temple.edu/~dbyzalov/

Sudipta Basu

Temple University - Department of Accounting ( email )

Philadelphia, PA 19122
United States
215.204.0489 (Phone)
215.204.5587 (Fax)

Register to save articles to
your library

Register

Paper statistics

Downloads
98
rank
262,948
Abstract Views
454
PlumX Metrics