Open Access
Classification and Regression by randomForest
Andy Liaw,Matthew C. Wiener +1 more
Reads0
Chats0
TLDR
random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.Abstract:
Recently there has been a lot of interest in “ensemble learning” — methods that generate many classifiers and aggregate their results. Two well-known methods are boosting (see, e.g., Shapire et al., 1998) and bagging Breiman (1996) of classification trees. In boosting, successive trees give extra weight to points incorrectly predicted by earlier predictors. In the end, a weighted vote is taken for prediction. In bagging, successive trees do not depend on earlier trees — each is independently constructed using a bootstrap sample of the data set. In the end, a simple majority vote is taken for prediction. Breiman (2001) proposed random forests, which add an additional layer of randomness to bagging. In addition to constructing each tree using a different bootstrap sample of the data, random forests change how the classification or regression trees are constructed. In standard trees, each node is split using the best split among all variables. In a random forest, each node is split using the best among a subset of predictors randomly chosen at that node. This somewhat counterintuitive strategy turns out to perform very well compared to many other classifiers, including discriminant analysis, support vector machines and neural networks, and is robust against overfitting (Breiman, 2001). In addition, it is very user-friendly in the sense that it has only two parameters (the number of variables in the random subset at each node and the number of trees in the forest), and is usually not very sensitive to their values. The randomForest package provides an R interface to the Fortran programs by Breiman and Cutler (available at http://www.stat.berkeley.edu/ users/breiman/). This article provides a brief introduction to the usage and features of the R functions.read more
Citations
More filters
Journal ArticleDOI
Random Forests and Kernel Methods
TL;DR: In this article, a connection between the random forests and the kernel methods is made, and it is shown empirically that the KeRF estimates compare favourably to the random forest estimates.
Journal ArticleDOI
Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models
TL;DR: The best-performing machine-learning model, random forest, has significantly higher predictive accuracy than multinomial logit and mixed logit models, and the random forest model produces behaviorally unreasonable arc elasticities and marginal effects when these behavioral outputs are computed from a standard approach.
Journal ArticleDOI
Predicting the risk of unplanned readmission or death within 30 days of discharge after a heart failure hospitalization
Anita G. Au,Finlay A. McAlister,Finlay A. McAlister,Jeffrey A. Bakal,Jeffrey A. Bakal,Justin A. Ezekowitz,Justin A. Ezekowitz,Padma Kaul,Padma Kaul,Carl van Walraven,Carl van Walraven +10 more
TL;DR: None of the administrative database models evaluated are sufficiently accurate to be used to identify which HF patients require extra resources at discharge, and models which incorporate length of stay such as the LaCE appear superior to current CMS-endorsed models for risk adjusting the outcome of "death or readmission within 30 days of discharge.
Journal ArticleDOI
Genomic Selection for Processing and End-Use Quality Traits in the CIMMYT Spring Bread Wheat Breeding Program
Sarah Battenfield,Carlos Guzmán,R. Chris Gaynor,Ravi P. Singh,Roberto J. Peña,Susanne Dreisigacker,Allan K. Fritz,Jesse Poland +7 more
TL;DR: Dough and loaf traits have moderately high predictive ability in CIMMYT breeding program and genomic selection genetic gain 1.4 to 2.7 times higher than phenotypic selection.
Journal ArticleDOI
A comparison of absolute performance of different correlative and mechanistic species distribution models in an independent area
TL;DR: The utilization of sensitivity and the fractional predicted areas showed that GLM, MaxEnt, Bioclim, and CL had the highest sensitivity for Australian climate conditions, while RF and BRT were poor.
References
More filters
Modern Applied Statistics With S
TL;DR: The modern applied statistics with s is universally compatible with any devices to read, and is available in the digital library an online access to it is set as public so you can download it instantly.
Proceedings Article
Boosting the margin: A new explanation for the effectiveness of voting methods
TL;DR: In this paper, the authors show that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero.
Journal ArticleDOI
Estimating Generalization Error on Two-Class Datasets Using Out-of-Bag Estimates
TL;DR: For two-class datasets, a method for estimating the generalization error of a bag using out-of-bag estimates is provided and most of the bias is eliminated and accuracy is increased by incorporating a correction based on the distribution of the out- of-bag votes.