Introducing Recursive Partitioning for Financial Classification: The Case of Financial Distress





    Search for more papers by this author
    • Assistant Professor of Statistics, Professor of Finance, Graduate School of Business Administration, New York University, and Senior Investment Analyst, General Motors Corporation, respectively. We are grateful to Professor Jerome Friedman for making the recursive partitioning computer program available to us and for a number of helpful suggestions. We are indebted to Burton Singer for stimulating discussions about the recursive partitioning approach. We thank the Salomon Brothers Center at the Graduate School of Business Administration, New York University, for financial support. We also thank an anonymous referee for constructive comments.


The purpose of this study is to present a new classification procedure, Recursive Partitioning Algorithm (RPA), for financial analysis and to compare it with discriminant analysis within the context of firm financial distress. RPA is a computerized, nonparametric technique based on pattern recognition which has attributes of both the classical univariate classification approach and multivariate procedures. RPA is found to outperform discriminant analysis in most original sample and holdout comparisons. We also observe that additional information can be derived by assessing both RPA and discriminant analysis results.