Mixed-effects random forest for clustered data

• Published in: Journal of statistical computation and simulation Vol. 84; no. 6; pp. 1313 - 1328
• Main Authors: Hajjem, Ahlem, Bellavance, François, Larocque, Denis
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 03-06-2014; Taylor & Francis Ltd
• Subjects: Algorithms; clustered data; Clustering; Computation; Computer simulation; Forests; mixed effects; Offices; random forest; Randomized algorithms; Regression analysis; regression tree; Revenues; Simulation
• ISSN: 0094-9655; 1563-5163
• DOI: 10.1080/00949655.2012.741599

This paper presents an extension of the random forest (RF) method to the case of clustered data. The proposed 'mixed-effects random forest' (MERF) is implemented using a standard RF algorithm within the framework of the expectation-maximization algorithm. Simulation results show that the proposed MERF method provides substantial improvements over standard RF when the random effects are non-negligible. The use of the method is illustrated to predict the first-week box office revenues of movies.