African Journal of
Business Management

  • Abbreviation: Afr. J. Bus. Manage.
  • Language: English
  • ISSN: 1993-8233
  • DOI: 10.5897/AJBM
  • Start Year: 2007
  • Published Articles: 4094

Full Length Research Paper

Financial distress prediction: Comparisons of logit models using receiver operating characteristic (ROC) curve analysis

  Mirfeyz Fallah Shams, Maryam Sheikhi and Zeinab Sheikhi      
Faculty of Management, Tehran Central Branch, Islamic Azad University, Tehran, Iran.
Email: [email protected]

  •  Accepted: 26 September 2011
  •  Published: 30 November 2011



The prediction of future financial condition of corporations has attracted the attention of financial researchers, and finding the alerting indexes of occurrence of financial distress has turned to be one of the most attractive and significant fields of financial and economic researches. Studying the history of researches shows that many of the researchers have focused on the financial ratios of the corporations to predict the financial distress. This article studies the logit models for one and two years before the occurrence of financial distress (T-1 and T-2) by making use of financial ratios and also by utilizing the analysis of receiver operating characteristic (ROC) curve. The analysis of ROC curve, among the models employed to compare the effectiveness of different statistical models, is often used in the fields of psychology and bio-medics in order to summarize the discriminatory of a diagnostic test and also to compare the performance of different models for binary outcomes. Regarding the accuracy of classification and prediction, the results of this research indicate that T-1 logit model is better than T-2 logit model. However, by considering the measurements done by ROC curve, it could be claimed that T-2 logit model operates more efficiently than T-1 logit model in the classification of distressed corporations.


Key words: Financial distress prediction, logit, receiver operating characteristic curve analysis, area under ROC curve (AUC).