The aim of the doctoral thesis is to screen possibilities of multivariate classification methods used for the prediction of a financial distress of agricultural enterprises. Application of the thesis was based on a definition of an enterprise threatened by financial distress defined according to relevant literature review. The reliability of current classification models was verified first as a part of the solution process. The ability of each indicator and their combinations in terms of reliability classification were assessed as well. The main part consisted in the construction of models using classification methods (linear and quadratic discriminant analysis and robust variants, the methods of nearest neighbours and prototypes, logistic regression, probit regression, multilayer perceptron networks, classification trees and forests).
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:113391 |
| Date | January 2012 |
| Creators | ZDENĚK, Radek |
| Source Sets | Czech ETDs |
| Language | Czech |
| Detected Language | English |
| Type | info:eu-repo/semantics/doctoralThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0023 seconds