Identification of corporate distress in UK industrials: a conditional probability analysis approach

Abstract

Multivariate discriminant analysis (MDA) has long been used to classify failing and non-failing firms with high accuracy rates, although a number of methodological flaws are well known. The alternative approach based on conditional probability analysis (CPA) models have been applied to forecast mergers and acquisitions and extended to the prediction of corporate failure. This is used here to distinguish between distressed and non-distressed companies in the UK industrial sector for the period 1985–1994. Results show that the CPA model is both efficient and consistent, has high accuracy levels and avoids the biased sampling problems that have been identified in MDA studies.