Journal of Scientific Papers

ECONOMICS & SOCIOLOGY


© CSR, 2008-2015
ISSN 2071-789X



Directory of Open Access Journals (DOAJ)


Strike Plagiarism

Partners
  • General Founder and Publisher:


    Centre of Sociological Research

  • Publishing Partners:

     
     
    University of Szczecin (Poland)


    Mykolas Romeris University (Lithuania)

     

     
     
    Alexander Dubcek University of Trencín, Faculty of Social and Economic Relations (Slovak Republic)



     
    University of Entrepreneurship and Law, (Czech Republic)

     

  • Membership:


    American Sociological Association


    European Sociological Association


    World Economics Association (WEA)

     


    CrossRef

     


Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction

Vol. 9, No 4, 2016

Matúš Mihalovič,

 

University of Economics in Bratislava,

Košice, Slovak Republic

matus.mihalovic@euke.sk

PERFORMANCE COMPARISON OF MULTIPLE DISCRIMINANT ANALYSIS AND LOGIT MODELS IN BANKRUPTCY PREDICTION

 

 

 

 

 

 

 

Abstract. 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.

 

Received: March, 2016

1st Revision: June, 2016

Accepted: November, 2016

 

DOI: 10.14254/2071-789X.2016/9-4/6

JEL Classification: G17, G32, G33, G34

Keywords: bankruptcy prediction, logistic regression, discriminant analysis, failure, classification accuracy.