Class Prediction by Nearest Shrunken Centroids, with Applications to DNA Microarrays

By Robert Tibshirani, Trevor J. Hastie, Balasubramanian Narasimhan, Gilbert Chu. 2003

476 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a27250cce7a494abafd25dcd4f6aa0b26dc1bb9b

How researchers see this paper

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

In Molecular Biology

Citations in the corpus

An extensive comparison of recent classification tools applied to microarray data (2004, methodology): “1 of Tibshirani et al. (2003) showed that, in LYM data, the average expression of FL and CLL subgroups are much more variable than that of DLCL.”
Supervised feature selection via dependence estimation (2007, methodology): “For example, we obtain the signal-to-noise ratio if the data is normalised by (sx+ +sx ). 4.4 Shrunken Centroid The shrunken centroid (pam) method [17, 18 ] performs feature ranking using the differences from the class centroids to the centroid of all the data.”
A Selective Overview of Variable Selection in High Dimensional Feature Space (2009, methodology): “To select important features, the two-sample t test is frequently employed (see, e.g., Tibshirani et al. (2003)).”
Comprehensive integration of single-cell data (2018, unknown): “…these experiments is generally much larger than the total number of features shared between the datasets, we opt for a diagonalized CCA implementation that has shown promising performance in related high-dimensional applications [Witten et al., 2009; Dudoit et al., 2002; Tibshirani et al., 2003].”
Integrating single-cell transcriptomic data across different conditions, technologies, and species (2018, methodology): “Therefore, we treat the covariance matrix within each data set as diagonal, a solution that has demonstrated promising results in other high-dimensional problems 59,60 .”
Mining data with random forests: A survey and results of new tests (2011, methodology): “centroids [66]; MARS: multivariate adaptive regression splines; CPNN: counterpropa”
Accurate Cancer Classification Using Expressions of Very Few Genes (2007, methodology): “In 2003, Tibshirani et al. successfully classified the lymphoma data set [5] with only 48 genes by using a statistical method called nearest shrunken centroids with an accuracy of 100 percent [ 6 ].”
The caret Package (2007, methodology): “• The nearest shrunken centroid model of Tibshirani et al (2003) is speciﬁed using method = "pam" .”
Penalized Model-Based Clustering with Application to Variable Selection (2007, methodology): “As a comparison, we applied the nearest shrunken centroids (NSC) (Tibshirani et al., 2003), random forests (RF) (Breiman, 2001), and support vector machines (SVM) (Vapnik, 1998), and thus treating the problem as supervised learning; the NSC was specifically developed for classification with gene…”
Regularized linear discriminant analysis and its application in microarrays. (2007, methodology): “This method generalizes the idea of the “nearest shrunken centroids” (NSC) (Tibshirani et al., 2003) into the classical discriminant analysis.”
Ultrahigh dimensional feature selection: beyond the linear model (2009, methodology): “This also applies for the LASSO and Nearest Shrunken Centroid (NSC, Tibshirani et al., 2003) methods which we include for comparison; instead of using SIS, this method regularizes the log-likelihood with an L 1 -penalty.”
A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. (2009, unknown): “Dudoit et al. (2001), Tibshirani, Hastie, Narasimhan & Chu (2003) .”
Semi-Supervised Methods to Predict Patient Survival from Gene Expression Data (2004, methodology): “In this study, we will use the ‘‘ nearest shrunken centroids ’’ procedure of Tibshirani et al. (2002), which is implemented in the package PAM (Tibshirani et al. 2003).”
Support vector machines : theory and applications (2005, methodology): “For the lymphoma data set, nearest shrunken centroids [29] used 48 genes to give a 100% accurate classification.”