Modelowanie upadłości przedsiębiorstw oparte na próbach niezbilansowanych
Modeling corporate bankruptcy based on unbalanced samples

Summary/Abstract: The aim of this article is to assess the efficiency of selected methods of multivariate statistical analysis in predicting bankruptcy of enterprises. The results of the classification of methods: classification trees and discriminate analysis, were compared. This article is a continuation of the author’s research on models of corporate bankruptcy, which involved sample balanced, i.e. those where the ratio between the bankrupt and no-bankrupt is 1:1. Forecasting results was that time based on unbalanced samples. Each company was described by means of diagnostic variables used as financial ratios. Analysis’ data were collected on the basis of information located in the database of Emerging Markets Information Service (EMIS).

• Details
• Contents