Random forest for ordinal responses: Prediction and variable selection

• Published in: Computational statistics & data analysis Vol. 96; pp. 57 - 73
• Main Authors: Janitza, Silke, Tutz, Gerhard, Boulesteix, Anne-Laure
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2016
• Subjects: Feature selection; Ordinal regression trees; Ordinal response; Prediction; Random forest; Variable importance; Feature selection; Random forest; Variable importance; Ordinal response; Prediction; Ordinal regression trees

The random forest method is a commonly used tool for classification with high-dimensional data that is able to rank candidate predictors through its inbuilt variable importance measures. It can be applied to various kinds of regression problems including nominal, metric and survival response variabl...