Bagging survival trees

By Torsten Hothorn, Berthold Lausen, Axel Benner, M. Radespiel-Tröger. 2004

268 citations recorded by the source corpus.

Subfields: Cancer Research, Molecular Biology, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cancer Research

1. Wei-Yin Loh
2. Ulrike Grömping
3. Julie Tibshirani
4. Susan Athey
5. Stefan Wager
6. Sandrine Dudoit

In Molecular Biology

1. Wei-Yin Loh
2. Ulrike Grömping
3. Stefan Wager
4. Susan Athey
5. Julie Tibshirani
6. Annette M. Molinaro
7. Hatem Ben-Ameur
8. Imad Bou-Hamad

In Statistics and Probability

1. Susan Athey
2. Stefan Wager
3. Wei-Yin Loh
4. Guido W. Imbens
5. Julie Tibshirani
6. Achim Zeileis
7. Torsten Hothorn
8. Mihaela van der Schaar

Citations in the corpus

• Local Linear Forests (2018, positive): “As in Athey, Tibshirani, and Wager (2019), we frame our discussion in terms of the Neyman–Rubin causal model (Imbens and Rubin 2015).”
• Generalized random forests (2016, methodology): “As in Hothorn et al. (2004) and Meinshausen (2006), our generalized random forests obtain such weights by averaging neighborhoods implicitly produced by different trees.”
• Distributional regression forests for probabilistic precipitation forecasting in complex terrain (2018, methodology): “Nearest neighbor weights are employed for aggregation in survival forests (Hothorn et al., 2004), quantile regression forests (Meinshausen, 2006), transformation forests (Hothorn and Zeileis, 2017), and generalized random forests for causal inferences (Athey, Tibshirani and Wager, 2019).”
• Algorithm runtime prediction: Methods & evaluation (2012, methodology): “Random forests (RFs) have previously been adapted to handle censored data [102,44], but the classical methods yield non-parametric Kaplan–Meier estimators that are undefined beyond the largest uncensored data point.”
• A review of survival trees (2011, methodology): “Hothorn et al. (2004) propose a general bagging method for an arbitrary tree growing algorithm but use the Leblanc and Crowley (1992) method for their practical implementation.”
• Variable Importance Assessment in Regression: Linear Regression versus Random Forest (2009, methodology): “KEY WORDS: Linear model; Random forest; Variable importance.”
• Tree-based multivariate regression and density estimation with right-censored data (2004, methodology): “[12] consider bagging the survival trees produced by the aforementioned procedures, with the aim of generating improved estimators of the conditional survival function.”
• Machine Learning for Survival Analysis: A Survey (2017, methodology): “In bagging survival trees, the aggregated survival function can be calculated by averaging the predictions made by a single survival tree instead of taking a majority vote [Hothorn et al. 2004].”
• Fifty Years of Classification and Regression Trees (2014, methodology): “Hothorn et al. (2004) used bagging to obtain an ensemble of survival trees and obtained a Kaplan–Meier survival curve for each subject from the bootstrap observations belonging to the same terminal nodes as the subject.”
• Survival ensembles. (2006, unknown): “Previous attempts to apply the main ideas to survival time data were bound to established key ingredients, such as the partial likelihood (Ridgeway, 1999), the Brier score for censored data (Benner, 2002), or survival trees (Hothorn et al., 2004; Ishwaran et al., 2004) and, consequently, inherited t”
• Ensemble deep learning: A review (2021, methodology): “survival trees [53] used Kaplan–Meier curve to predict the ensemble output for breast cancer”