Many models are in existence that use publicly available company accounting data to construct and weight financial ratios that when aggregated comprise a “z‐score”. This score is used to classify companies as going concerns or bankrupt concerns. These models have generally been very successful in their classification performance. However, ratios can be inherently ill‐conditioned, because dominators can be small relative to particular numerators. Also numerators and denominators can have the wrong sign. When any of these events occur the z‐score is distorted, and therefore the model's classifications unreliable. Examples are given of companies where these phenomena have arisen. It is argued that it is quite common in extant companies. The authors suggest that in such circumstances different models are required to analyse company performance. They suggest that z‐score models ought to be developed where the ratios that comprise the z‐score are naturally bounded, and therefore incapable of displaying such ill conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.