Predicting Corporate Bankruptcy: An Evaluation of Alternative Statistical Frameworks

Corporate bankruptcy prediction has attracted significant research attention from business academics, regulators and financial economists over the past five decades. However, much of this literature has relied on quite simplistic classifiers such as logistic regression and linear discriminant analysis (LDA). Based on a large sample of US corporate bankruptcies, we examine the predictive performance of 16 classifiers, ranging from the most restrictive classifiers (such as logit, probit and linear discriminant analysis) to more advanced techniques such as neural networks, support vector machines (SVMs) and “new age” statistical learning models including generalised boosting, AdaBoost and random forests. Consistent with the findings of Jones et al. ( 2015 ), we show that quite simple classifiers such as logit and LDA perform reasonably well in bankruptcy prediction. However, we recommend the use of “new age” classifiers in corporate bankruptcy modelling because: (1) they predict significantly better than all other classifiers on both the cross‐sectional and longitudinal test samples; (2) the models may have considerable practical appeal because they are relatively easy to estimate and implement (for instance, they require minimal researcher intervention for data preparation, variable selection and model architecture specification); and (3) while the underlying model structures can be very complex, we demonstrate that “new age” classifiers have a reasonably good level of interpretability through such metrics as relative variable importances (RVIs).     

A faster estimation method for the probability of informed trading using hierarchical agglomerative clustering

The probability of informed trading (PIN) is a commonly used market microstructure measure for detecting the level of information asymmetry. Estimating PIN can be problematic due to corner solutions, local maxima and floating point exceptions (FPE). Yan and Zhang [J. Bank. Finance, 2012, 36, 454–467] show that whilst factorization can solve FPE, boundary solutions appear frequently in maximum likelihood estimation for PIN. A grid search initial value algorithm is suggested to overcome this problem. We present a faster method for reducing the likelihood of boundary solutions and local maxima based on hierarchical agglomerative clustering (HAC). We show that HAC can be used to determine an accurate and fast starting value approximation for PIN. This assists the maximum likelihood estimation process in both speed and accuracy.     

An empirical analysis of air pollution emissions policy for the U.K. residential sector

In this paper an analysis of the U.K. government's air pollution emissions policy for the residential sector is undertaken. The analysis covers emissions arising from water and space heating, electric appliances and cooking appliances. Using an integrated economic-engineering model, the effects of the Energy Savings Trust and the imposition of Value Added Tax on residential fuel will be evaluated in terms of energy consumption and pollution emissions. It is found that the initial proposed policy was not sufficiently stringent to meet the government's environmental objectives, and that subsequent events have undermined the government's programme even further. Unless alternative policies are introduced, emissions from the residential sector will play an important role in jeopardizing the ability of the U.K. government to meet its international obligations.     

Typology formation across socio-economic indicators

Some decisions in planning and policy formation require the comparison of one region or country with another. If the entities being compared are known and have been demonstrated to be either similar or different, then valid comparisons can be made. Unfortunately, many comparisons are made on an ad hoc and often improper basis. The paper describes a method of typology formation which requires the modification and the use of the Euclidean distance measure calculated between countries over a series of social indicators. The potential usefulness of the method is demonstrated by reference to an example using indicators of educational system provision.     

Sensitivity Analysis And Schemes Of Arrangement

Formal mathematical techniques are being used increasingly as aids to commercial decision-making. We propose that those deciding whether to liquidate or trade-out should, as a matter of course, have sufficient information to enable sensitivity analysis on any forecast returns. Sensitivity analyses are notably lacking in documentation used for predicting the outcomes of schemes of arrangement such as the complex Estate Mortgage Trusts (EMT) moratorium on the withdrawal of funds by unitholders. This article details the outcomes of some schemes of arrangement in Australia in the 1960s and 1970s and discusses the EMT moratorium. The moratorium procedures provide the setting and data for simulations and sensitivity analyses. Coupled with the evidence provided by Dean (1977, 1983) and Aitken (1981), this suggests a need for information on the expected timing of payouts to enable sensitivity analysis whenever a scheme involves delayed distributions.     

Asymmetric impact of earnings news on investor uncertainty

We describe a model that predicts an asymmetric impact of disclosure on investor uncertainty. We show that good news tends to resolve more uncertainty than bad news, and that uncertainty can be revised upwards if the investors' prior belief is sufficiently strong and the signal is sufficiently bad. This result is in contrast to classical disclosure models, where new information always resolves uncertainty and the change in uncertainty depends only on the relative precision of the news. Using option-implied volatility as a proxy for uncertainty, we find strong support for our predictions. We also show that our results are robust to competing explanations, notably to the leverage effect and volatility feedback, as well as to the jump risk induced in anticipation of the earnings announcements.     

Cooperation or resistance? Representing workers' health and safety in a hazardous industry

This study considers the actions of worker health and safety representatives in coalmines in Queensland, where there is little evidence of the facilitating role of management previous studies have associated with the successful operation of worker representation in occupational health and safety. It examines how worker representatives deliver their pluralist representational role in a context characterised by essentially unitary thinking amongst their employers and the effectiveness of the strategies they use.