Bankruptcy prediction models: a comparative study of the Baltic listed companies

Abstract

Purpose – The purpose of the research is to evaluate performance of seven commonly applied bankruptcy prediction models in the Baltic listed companies and how these models can be applied in investment decision-making process.

Design/methodology/approach – Analysis is conducted on a sample of 75 listed companies (Baltic Stock Exchange) over the period from 2002 to 2011. The research methods: monographic, graphical, analysis of statistical data, correlation and comparative analysis.

Findings – The lowest type II error is obtained by the Zmijewski model (type II error is less than 20%) regardless of the point in the business cycle. Low type II error is shown also by Altman Z’ and Altman Z’’ models during the economic upward phase, however type II error is sensitive to the changes of the business cycle and increases significantly during economic downturn. The results of correlation analysis show that if type II error increases for one model, then same can be expected for other models. The authors recommend using Zmijewski model in investment decision-making process and as a rule of thumb to use at least two models (with the smallest type I and II errors); however, during the economic downturn it is not advisable to use any model at all.

Research limitations/implications – Type I error occurs when a model does not predict bankruptcy. Type II error means that the model mis-predicted a solvent company as bankrupt. This paper evaluates and analyses mostly type II error.

Practical implications – The results of this paper can be used to evalute the effectiveness of several bankruptcy prediction models for the Baltic listed companies, and how they can be applied in the investment decision-making process.

Originality/value – Authors of the paper focus on type II error, previous research by other authors is mainly concerned with type I error. In addition this study is innovative, because type II error dynamics are analyzed within the business cycle change.