Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises
The purpose of the article. The aim of this study is to predict bankruptcy among Polish non-financial firms by constructing discriminant models and comparing the outcomes with prognostic models developed by other Polish scholars. Utilizing financial data from 2017–2021 for 416 companies across the t...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
Lodz University Press
2024-12-01
|
| Series: | Finanse i Prawo Finansowe |
| Subjects: | |
| Online Access: | https://czasopisma.uni.lodz.pl/fipf/article/view/24536 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556113411014656 |
|---|---|
| author | Bernard Kokczyński |
| author_facet | Bernard Kokczyński |
| author_sort | Bernard Kokczyński |
| collection | DOAJ |
| description | The purpose of the article. The aim of this study is to predict bankruptcy among Polish non-financial firms by constructing discriminant models and comparing the outcomes with prognostic models developed by other Polish scholars. Utilizing financial data from 2017–2021 for 416 companies across the trade, production, and service sectors, this research strives to devise the most effective model for classifying entities into two groups.
Methodology. The study employed a discriminant function, a statistical method enabling the classification of objects based on several explanatory variables simultaneously. Two methods for selecting independent variables for the discriminant function were compared using group mean equality tests and Hellwig's method. Additionally, two techniques of winsorization were applied to minimize the impact of outliers on the study results.
Results of the research. The study’s findings underscore the importance of operational profitability relative to total assets and the logarithm of total assets as key variables in bankruptcy prediction models. Results confirm the significance of industry specificity on the models' classification accuracy. The use of different methods for selecting independent variables for models and winsorization directly impacts classification efficacy. A comparative analysis with models from selected Polish researchers reveals that the models developed in this study achieved a higher level of effectiveness than existing models in terms of classification accuracy. |
| format | Article |
| id | doaj-art-ae46bb2726444256bdd8db0d21ae25e3 |
| institution | Kabale University |
| issn | 2391-6478 2353-5601 |
| language | deu |
| publishDate | 2024-12-01 |
| publisher | Lodz University Press |
| record_format | Article |
| series | Finanse i Prawo Finansowe |
| spelling | doaj-art-ae46bb2726444256bdd8db0d21ae25e32025-01-07T13:55:19ZdeuLodz University PressFinanse i Prawo Finansowe2391-64782353-56012024-12-01444799310.18778/2391-6478.4.44.0525031Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public EnterprisesBernard Kokczyński0https://orcid.org/0000-0002-9379-0376University of Lodz The purpose of the article. The aim of this study is to predict bankruptcy among Polish non-financial firms by constructing discriminant models and comparing the outcomes with prognostic models developed by other Polish scholars. Utilizing financial data from 2017–2021 for 416 companies across the trade, production, and service sectors, this research strives to devise the most effective model for classifying entities into two groups. Methodology. The study employed a discriminant function, a statistical method enabling the classification of objects based on several explanatory variables simultaneously. Two methods for selecting independent variables for the discriminant function were compared using group mean equality tests and Hellwig's method. Additionally, two techniques of winsorization were applied to minimize the impact of outliers on the study results. Results of the research. The study’s findings underscore the importance of operational profitability relative to total assets and the logarithm of total assets as key variables in bankruptcy prediction models. Results confirm the significance of industry specificity on the models' classification accuracy. The use of different methods for selecting independent variables for models and winsorization directly impacts classification efficacy. A comparative analysis with models from selected Polish researchers reveals that the models developed in this study achieved a higher level of effectiveness than existing models in terms of classification accuracy.https://czasopisma.uni.lodz.pl/fipf/article/view/24536bankruptcy prediction modelswinsorization of datanon-financial informationmethods of selecting variables for models |
| spellingShingle | Bernard Kokczyński Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises Finanse i Prawo Finansowe bankruptcy prediction models winsorization of data non-financial information methods of selecting variables for models |
| title | Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises |
| title_full | Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises |
| title_fullStr | Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises |
| title_full_unstemmed | Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises |
| title_short | Construction of Discrimination Models in Prediction of Bankruptcy if Polish Non-Public Enterprises |
| title_sort | construction of discrimination models in prediction of bankruptcy if polish non public enterprises |
| topic | bankruptcy prediction models winsorization of data non-financial information methods of selecting variables for models |
| url | https://czasopisma.uni.lodz.pl/fipf/article/view/24536 |
| work_keys_str_mv | AT bernardkokczynski constructionofdiscriminationmodelsinpredictionofbankruptcyifpolishnonpublicenterprises |