作者: HALINA FRYDMAN , EDWARD I. ALTMAN , DUEN-LI KAO
DOI: 10.1111/J.1540-6261.1985.TB04949.X
关键词: Nonparametric statistics 、 Machine learning 、 Pattern recognition (psychology) 、 Econometrics 、 Financial analysis 、 Multivariate statistics 、 Context (language use) 、 Recursive partitioning 、 Linear discriminant analysis 、 Univariate 、 Computer science 、 Artificial intelligence
摘要: The purpose of this study is to present a new classification procedure, Recursive Partitioning Algorithm (RPA), for financial analysis and compare it with discriminant within the context firm distress. RPA computerized, nonparametric technique based on pattern recognition which has attributes both classical univariate approach multivariate procedures. found outperform in most original sample holdout comparisons. We also observe that additional information can be derived by assessing results.