An Empirical Study of Bank Stress Testing for Auto Loans

42 Pages Posted: 8 Apr 2015 Last revised: 4 Oct 2018

See all articles by Deming Wu

Deming Wu

Government of the United States of America - Office of the Comptroller of the Currency (OCC)

Ming Fang

Martin Tuchman School of Management, New Jersey Institute of Technology

Qing Wang

Southwestern University of Finance and Economics (SWUFE)

Date Written: June 1, 2018

Abstract

We present an empirical study of stress testing for portfolios of auto loans. We find that loans aged five years or more have significantly higher default probabilities. This finding raises concerns about the increasing maturity of auto loans in recent years. A challenge in stress testing is the instability of the estimated coefficient of macroeconomic variables, which raises questions on the reliability of stress test results. For this reason, it is important for model developers to perform sensitivity analyses and make conservative adjustment to minimize model risk.

Keywords: Auto loan defaults, stress testing, model instability, loan age, macroeconomic variables, used car prices

JEL Classification: G21, G28, G18, G32

Suggested Citation

Wu, Deming and Fang, Ming and Wang, Qing, An Empirical Study of Bank Stress Testing for Auto Loans (June 1, 2018). Journal of Financial Stability, Forthcoming. Available at SSRN: https://ssrn.com/abstract=2591361 or http://dx.doi.org/10.2139/ssrn.2591361

Deming Wu (Contact Author)

Government of the United States of America - Office of the Comptroller of the Currency (OCC) ( email )

400 7th Street SW
Washington, DC 20219
United States

Ming Fang

Martin Tuchman School of Management, New Jersey Institute of Technology ( email )

United States

Qing Wang

Southwestern University of Finance and Economics (SWUFE) ( email )

Chengdu
China

Register to save articles to
your library

Register

Paper statistics

Downloads
421
Abstract Views
1,881
rank
70,194
PlumX Metrics