Economics & Sociology

ISSN: 2071-789X eISSN: 2306-3459 DOI: 10.14254/2071-789X
Index PUBMS: f5512f57-a601-11e7-8f0e-080027f4daa0
Article information
Title: Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction
Issue: Vol. 9, No 4, 2016
Published date: 12-2016 (print) / 12-2016 (online)
Journal: Economics & Sociology
ISSN: 2071-789X, eISSN: 2306-3459
Authors: Matúš Mihalovič
Keywords: bankruptcy prediction, logistic regression, discriminant analysis, failure, classification accuracy
DOI: 10.14254/2071-789X.2016/9-4/6
Index PUBMS: 88265ee1-0209-11e8-94c4-fa163e5d4f72
Language: English
Pages: 101-118 (18)
JEL classification: G17, G32, G33, G34

In this study, the attention is dedicated to the development of bankruptcy prediction model in Slovak Republic. The presented paper focuses on the comparison of overall prediction performance of the two developed models. The first one is estimated via discriminant analysis, while the another is based on a logistic regression. The sample is made up of 236 firms operating in Slovakia, divided into two groups – failed and non-failed firms. The results of the study suggest that the model based on a logit function outperforms the classification accuracy of the discriminant model. The most significant predictors of impeding firms´ failure appear to be Net Income to Total Assets, Current Ratio and Current liabilities to Total Assets.