The financial crises of 2008 increased the focus around financial distress and even more so on predicting financially distressed companies prior to the fact. This research paper investigates using recursive partitioning to predict financially distressed companies on the Johannesburg Stock Exchange, taking different business cycle periods into account over the time period 1997-2014. The updated as well as longer time period over which the analysis is conducted distinguishes this research paper from prior research. This paper employs both the CART and CHAID algorithm and obtains financially distressed prediction models which have a higher correct classification rate than chance alone and prior literature in South Africa. This paper also makes use of a matched data sample approach and the manner in which missing data is addressed makes a valuable contribution to financial distress prediction research. Furthermore, support is found for prior literature in that financial variables are statistically significant in predicting financial distress.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:uct/oai:localhost:11427/20633 |
| Date | January 2016 |
| Creators | Smit, Candice |
| Contributors | Van Rensburg, Paul |
| Publisher | University of Cape Town, Faculty of Commerce, Department of Finance and Tax |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Master Thesis, Masters, MCom |
| Format | application/pdf |
Page generated in 0.002 seconds