Industry-relative financial ratios have received increasing attention in financial modelling. This is because these ratios have been deemed useful when comparing the success of firms belonging to different industries. This is important, for instance, when testing bankruptcy prediction models in cross-sectional financial ratio analysis. We focus on the time-series stability of interrelationships between industry-relative ratios. First, cross-sectional financial ratio patterns are estimated by applying factor analysis. Secondly, transformation analysis is used to investigate the time-series stability of these cross-sectional ratio patterns. It is discovered that the use of industry-relative ratios leads to a considerably increased level of instability in interrelationships between ratios. This decreases the accuracy of multivariate prediction models using industry-relative ratios.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Theoretical Computer Science
- Computer Science Applications