Predicting Corporate Failure of UK's Listed Companies

This study compares two corporate failure prediction models, namely; multiple discriminant analysis (MDA) and logistic regression (Logit) in an attempt to; identify whether or not financial ratios can be used as indicators of failure in the UK, to identify financial ratios that are most important for detecting potential insolvency of UK's public listed companies and also which model is better in predicting corporate failure. The study employed financial information for a group of 50 distressed and 50 non-distressed UK listed companies during the period 2000-2010. The initial sample of 100 companies was divided into a 70% estimation (training) sample and a 30% holdout (test) sample for the following 4 data sets: First-year data set to predict failure, a second-year data set for a 2 year-ahead prediction, third-year data for a 3 year-ahead prediction, as well as cumulative three-year data to predict distress 1 year ahead by letting the ratios vary in time. For each company, a set of 19 financial ratios reflecting the company's profitability, solvency, asset utilisation, growth ability and size, were calculated and then used in the study.