Hüttemann, Martin (2019). Three Essays on Corporate Bankruptcies and their Prediction. PhD thesis, Universität zu Köln.

[img]
Preview
PDF
phdthesis_Huettemann.pdf

Download (1MB) | Preview

Abstract

This thesis comprises three essays on corporate bankruptcies, their characteristics, their collection, and their prediction. In particular, it focuses on (1) the improvement in the performance of bankruptcy prediction models through the construction of a predictor variable, (2) the impact of data quality on the estimation and the evaluation of bankruptcy prediction models, and (3) the characteristics and implications of a typical bankruptcy proceeding. In the first essay, we develop a model to predict bankruptcies, exploiting that negative book equity is a strong indicator of financial distress. Accordingly, our key predictor of bankruptcy is the probability that future losses will deplete a firm’s book equity. To calculate this probability, we use earnings forecasts and their standard deviations obtained from cross-sectional regression models in the spirit of Hou, van Dijk, and Zhang (2012). We add variables that we find to discriminate between bankrupt and non-bankrupt firms. As our model requires only accounting data, we can provide bankruptcy predictions for a wide range of firms, including firms that have no access to capital markets. In strictly out-of-sample tests, we show that our accounting model performs better than alternative corporate failure models that use only accounting information. If we additionally allow for stock market information, our approach also outperforms leading alternatives that require market data. The second essay assesses the quality of bankruptcy data and its impact on the estimation and evaluation of prediction models. We develop a systematic methodology to obtain bankruptcy information from corporate news releases and public sources. Applying this methodology to the German market, we create a bankruptcy database with a greater number of bankruptcy events as well as more accurate bankruptcy events and more accurate bankruptcy dates than those in the frequently used databases of Bureau van Dijk and Compustat Global. We use our bankruptcy data to conduct two empirical analyses. First, we compare the performance of several bankruptcy prediction models in the German market. Second, we compare our database with Bureau van Dijk data and find that the quality of bankruptcy data significantly affects parameter estimates and the out-of-sample evaluation of bankruptcy prediction models. Therefore, we suggest revising the evidence presented by bankruptcy studies that are based on inaccurate information. By crawling the German business register, the third essay creates a dataset that involves the type and timing of German firms’ bankruptcy events. This dataset is then used to make five primary contributions. First, I describe the characteristics of typical bankruptcy proceedings and disclose the differences between joint-stock and limited liability firms. Second, I combine bankruptcy and annual report dates to demonstrate that opening a bankruptcy proceeding impacts annual report publication dates. Third, I quantify the bias that arises due to legal deletion requirements of bankruptcy data from the business register. Simultaneously, I show that in recent years, crawling the business register yields more bankruptcies than using Bureau van Dijk’s database. Thus, regularly crawling the business register may yield a more complete database. Fourth, I use a large sample of 213,455 firm-years to compare bankruptcy prediction models for both public and private German firms. Fifth, splitting the sample into small, medium-sized, and large firms, I show the impact of firm size on prediction model results.

Item Type: Thesis (PhD thesis)
Creators:
CreatorsEmailORCID
Hüttemann, Martinhuettemann@wiso.uni-koeln.deUNSPECIFIED
URN: urn:nbn:de:hbz:38-97704
Subjects: Management and auxiliary services
Uncontrolled Keywords:
KeywordsLanguage
bankruptcy prediction, negative book equity, mechanical earnings forecasts, financial distress, data quality, data collection, bankruptcy events, public firms, private firms, bankruptcy proceedings, annual reportsEnglish
Faculty: Faculty of Management, Economy and Social Sciences
Divisions: Faculty of Management, Economics and Social Sciences > Business Administration > Finance > Professorship for Business Administration and Corporate Finance
Language: English
Date: 2019
Date of oral exam: 6 June 2019
Referee:
NameAcademic Title
Hess, DieterProf. Dr.
Hartmann-Wendels, ThomasProf. Dr.
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/9770

Downloads

Downloads per month over past year

Export

Actions (login required)

View Item View Item