A growing number of applications of random forests in psychology indicates a wide range of application areas in this field, as well: For example, Oh, Laubach, and Luczak (2003) and Shen, Ong, Li, Hui, and Wilder-Smith (2007) apply random forests to neuronal ensemble recordings and EEG data, that are too high-dimensional for the application of standard regression methods. An alternative approach to cope with large numbers of predictor variables would be to first apply dimension reduction techniques, such as principle components or factor analysis, and then use standard regression methods on the reduced data set. However, this approach has the disadvantage that the original input variables are projected into a reduced set of components, so that their individual effect is not longer identifiable. As opposed to that, random forests can process large numbers of predictor variables simultaneously and provide individual measures of variable importance.
