The objective of this study is to introduce a more refined methodological approach for signalling corporate collapse. The proposed methodological approach provides informed stakeholders in a corporation with a tool that would help them signal impending collapse with a higher degree of accuracy than the existing mainstream methodology. By doing so, the proposed methodological approach helps stakeholders take appropriate measures, if possible, to save their company from collapse.
The motivation behind this study emanates from a need in the literature in relation to coming up with a new methodological approach that is superior to what is available. For example, Jones and Hensher (2004), one of the most recent studies in the field, stated that over the past three decades there has been a conspicuous absence of modelling innovation in the literature on financial distress prediction, as well as a failure to keep abreast of important methodological developments emerging in other fields of the social sciences.
Specifically, this study introduces a new ratio-based multivariate methodological approach for signalling corporate collapse, called Multi-Level Modelling (MLM). Moreover, this study demonstrated that MLM provides informed stakeholders in a corporation with a tool that would help them signal impending collapse with a higher degree of accuracy than Multiple Discriminant Analysis (MDA), which is the mainstream benchmark methodological approach. By doing so, MLM helps stakeholders take appropriate measures, if possible, to save their company from collapse.
The empirical results depicted the superiority of MLM over MDA. MLM generated better overall predictive power and dramatically reduced the occurrence of Type I error (classifying a collapsed company as non-collapsed). Moreover, MLM achieved those results while at the same time capturing variations in industry sectors among the data sample of companies. This is something that MDA was not capable of.
Identifer | oai:union.ndltd.org:ADTP/216552 |
Date | January 2006 |
Creators | Hossari, Ghassan, hossari7@bigpond.net.au |
Publisher | Swinburne University of Technology. Australian Graduate School of Entrepreneurship |
Source Sets | Australiasian Digital Theses Program |
Language | English |
Detected Language | English |
Rights | http://www.swin.edu.au/), Copyright Ghassan Hossari |
Page generated in 0.002 seconds