The effect of size on the failure probabilities of SMEs : an empirical study on the US market using discrete hazard model

El Kalak, Izidin; Hudson, Robert

Abstract

This paper investigates the extent to which the size affects the SME probabilities of bankruptcy. Using a dataset of (11,117) US non-financial firms, of which (465) filed for insolvency under chapters 7/11 between 1980 and 2013. We forecast the bankruptcy probabilities by developing four discrete-time duration-dependent hazard models for SMEs, Micro, Small, and Medium firms. A comparison of the default prediction models for medium firms and SMEs suggests that an almost identical set of explanatory variables affect the default probabilities leading us to believe that treating each of these groups separately has no material impact on the decision making process. However, comparisons between the micro and small firms with the SMEs firms strongly suggest that these categories need to be considered separately when modelling their credit risk.

Citation

El Kalak, I., & Hudson, R. (2016). The effect of size on the failure probabilities of SMEs : an empirical study on the US market using discrete hazard model. International review of financial analysis, 43(January), 135-145. https://doi.org/10.1016/j.irfa.2015.11.009

• Acceptance Date: Nov 20, 2015
• Online Publication Date: Nov 26, 2015
• Publication Date: 2016-01
• Deposit Date: Dec 17, 2015
• Publicly Available Date: Nov 23, 2017
• Journal: International review of financial analysis
• Print ISSN: 1057-5219
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 43
• Issue: January
• Pages: 135-145
• DOI: https://doi.org/10.1016/j.irfa.2015.11.009
• Keywords: SMEs; Bankruptcy; Size; Discrete-time duration-dependent hazard model; G200
• Public URL: https://hull-repository.worktribe.com/output/383000
• Publisher URL: http://www.sciencedirect.com/science/article/pii/S1057521915001994
• Additional Information: Authors' accepted manuscript of article published in: International review of financial analysis, 2016, v.43.
• Contract Date: Nov 23, 2017