Prediction of commercial bank failure via multivariate statistical analysis of financial structures: The Turkish case

Çanbaş, Serpil; Cabuk, Altan; Kılıç, Süleyman

doi:10.1016/j.ejor.2004.03.023

Cited by 257 publications

(141 citation statements)

References 16 publications

Supporting

Mentioning

131

Contrasting

Unclassified

Order By: Relevance

“…These studies include the work done by Canbas et al (2005), Celik and Karatepe (2007), Erdogan (2008), Boyacioglu et al (2009), Erdogan (2012, and Inan and Erdogan (2013). There are very few panel data applications for bank bankruptcy related to the Turkish bank system.…”

Section: Introductionmentioning

confidence: 99%

Long-term Examination of Bank Crashes Using Panel Logistic Regression: Turkish Banks Failure Case

Erdogan¹

2016

IJSP

View full text Add to dashboard Cite

Crises in the financial sector over the last two decades have shown the importance of early warning systems, especially for bank failures. This study aims to develop an early warning system for Turkish commercial bank failures using panel data from 2002 to 2012. The data was analyzed using pooled logistic regression versus random panel logistic regression. The dependent variable was the bank failure, defined as the return-on assets ratio. Factor analysis was used to construct independent variables of financial ratios. The meaningful factors were found as: Interest income and expenditures, Equity, Other income and expenditures, Balance sheet, Deposit, Due, Asset quality. When the focus is sensitivity, the best prediction performance was obtained using random-effect logistic regression.

show abstract

Section: Introductionmentioning

confidence: 99%

Long-term Examination of Bank Crashes Using Panel Logistic Regression: Turkish Banks Failure Case

Erdogan¹

2016

IJSP

View full text Add to dashboard Cite

show abstract

“…Cole and Gunther (1998), on the other hand, forecast bank failures applying a standard probit model to bank accounting data, whereas Crowley and Loviscek (1990) classify failures amongst small U.S. commercial banks that took place in 1984 using linear probability, logit, probit, and discriminant models. In a similar vein, Canbas et al (2005) combine the principal component analysis with discriminant analysis, probit and logit techniques to construct an integrated early warning system that can be utilised as a regulatory tool for the detection of banks that experience financial difficulties.…”

Section: Related Literaturementioning

confidence: 99%

To be bailed out or to be left to fail? A dynamic competing risks hazard analysis

Papanikolaou

2018

Journal of Financial Stability

View full text Add to dashboard Cite

During the late 2000s financial crisis, a large number of banks either failed or received financial aid thus inflicting substantial losses on the system. We contribute to the early warning literature by developing a dynamic competing risks hazard model that explores the joint determination of the probability of a distressed bank to face a licence withdrawal or to be bailed out. The underlying patterns of distress are analysed based on a broad range of bank-level and environmental factors. We find that institutions with inadequate capital, illiquid and risky assets, poor management, low levels of earnings and high sensitivity to market conditions have a higher probability to go bankrupt. Bailed out banks, on the other hand, face both capital and liquidity shortages, experience low earnings, and are highly exposed to market products; however, neither managerial expertise, nor the quality of assets are relevant to the odds of bailout. We further document that large and complex banks are less likely to fail and more likely to be bailed out and that authorities are more prone to provide support to a distressed bank, which is well-connected with politicians and political parties and less prone to let it go bankrupt. Importantly, our model outperforms the commonly used logit model in terms of forecasting accuracy in all the in-and out-of-sample tests we conduct.JEL Classification: C13; C53; D02; G01; G21.

show abstract

“…Based on the review carried out, several comments can be outlined: (i) the use of statistical procedures either for determining the optimal method or for comparing the performance of different prediction models appears to be infrequent since more than 68% of papers have not reported any form of hypothesis testing; (ii) the parametric tests have been applied in nearly 18% of papers (especially the t-test with about 15%), but ignoring whether the samples hold the normality and homoscedasticity assumptions or not; (iii) approximately 13% of papers have included a non-parametric test in the experimental protocol, being the McNemar's (5.67%) and Wilcoxon's signed-ranks (3.55%) tests the two most common techniques; (iv) only three papers (Canbas et al 2005;Abdou et al 2008;Abdou 2009a) have studied the statistical difference of variances through Bartlett's, Levene's or Cochran's C tests; and (v) the post hoc tests for comparisons with a control algorithm have seldom been applied, with only seven works using the Tukey's method (Pendharkar 2005), the Nemenyi's test (García et al 2012;Marqués et al 2013;Brown and Mues 2012), the Holm's test (Hu and Chen 2011) or the Bonferroni-Dunn's procedure (Marqués et al 2012a,b).…”

Section: Statistical Tests Of Significancementioning

confidence: 99%

An insight into the experimental design for credit risk and corporate bankruptcy prediction systems

2014

View full text Add to dashboard Cite

Over the last years, it has been observed an increasing interest of the finance and business communities in any application tool related to the prediction of credit and bankruptcy risk, probably due to the need of more robust decision-making systems capable of managing and analyzing complex data. As a result, plentiful techniques have been developed with the aim of producing accurate prediction models that are able to tackle these issues. However, the design of experiments to assess and compare these models has attracted little attention so far, even though it plays an important role in validating and supporting the theoretical evidence of performance. The experimental design should be done carefully for the results to hold significance; otherwise, it might be a potential source of misleading and contradictory conclusions about the benefits of using a particular prediction system. In this work, we review more than 140 papers published in refereed journals within the period 2000-2013, putting the emphasis on the bases of the experimental design in credit scoring and bankruptcy prediction applications. We provide some caveats and guidelines for the usage of databases, data splitting methods, performance evaluation metrics and hypothesis testing procedures in order to converge on a systematic, consistent validation standard.

show abstract

Prediction of commercial bank failure via multivariate statistical analysis of financial structures: The Turkish case

Cited by 257 publications

References 16 publications

Long-term Examination of Bank Crashes Using Panel Logistic Regression: Turkish Banks Failure Case

Long-term Examination of Bank Crashes Using Panel Logistic Regression: Turkish Banks Failure Case

To be bailed out or to be left to fail? A dynamic competing risks hazard analysis

An insight into the experimental design for credit risk and corporate bankruptcy prediction systems

Contact Info

Product

Resources

About