Share:


Prediction of default probability for construction firms using the logit model

    H. Ping Tserng Affiliation
    ; Po-Cheng Chen Affiliation
    ; Wen-Haw Huang Affiliation
    ; Man Cheng Lei Affiliation
    ; Quang Hung Tran Affiliation

Abstract

Recently, the high incidence of construction firm bankruptcies has underlined the importance of forecasting defaults in the construction industry. Early warning systems need to be developed to prevent or avert contractor default; additionally, this evaluation result could facilitate the selection of firms as collaboration or investment partners. Financial statements are considered one of the key basic evaluation tools for demonstrating firm strength. This investigation provides a framework for assessing the probability of construction contractor default based on financial ratios by using the Logit model. A total of 21 ratios, gathered into five financial groups, are utilized to perform univariate logit analysis and multivariate logit analysis for assessing contractor default probability. The empirical results indicate that using multivariate analysis by adding market factor to the liquidity, leverage, activity and profitability factors can increase the accuracy of default prediction more than using only four financial factors. While considering the market factor in the multivariate Logit model, clear incremental prediction performance appears in 1-year evaluation. This study thus suggests that the market factor comprises important information to increase the prediction performance of the model when applied to construction contractors, particularly in short-term evaluation.

Keyword : default probability, financial ratios, Logit model, bankruptcy prediction

How to Cite
Tserng, H. P., Chen, P.-C., Huang, W.-H., Lei, M. C., & Tran, Q. H. (2014). Prediction of default probability for construction firms using the logit model. Journal of Civil Engineering and Management, 20(2), 247-255. https://doi.org/10.3846/13923730.2013.801886
Published in Issue
Apr 24, 2014
Abstract Views
975
PDF Downloads
872
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.