Prediction by Supervised Principal Components

By Eric Bair, Trevor J. Hastie, Debashis Paul, Robert Tibshirani. 2006

860 citations recorded by the source corpus.

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

Sufficient Forecasting Using Factor Models (2015, methodology): “As an improvement to this procedure, Bair et al. (2006) used correlation screening to remove irrelevant predictors before performing the PCA.”
Sparse partial least squares regression for simultaneous dimension reduction and variable selection (2010, methodology): “The second simulation is referred to “hard simulation” by Bair et al. (2006), where more complicated hidden components are generated, and the rest of the data generation remains the same as the “simple simulation”.”
Sparse PLS discriminant analysis: biologically relevant feature selection and graphical displays for multiclass problems (2011, methodology): “This is the case of Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA, see [11,12] for a supervised version), Partial Least Squares Regression (PLS, [13], see also [14-16] for discrimination purposes), to explain most of the variance/covariance structure of the data using linear ”
Selecting Instrumental Variables in a Data Rich Environment (2009, methodology): “The method is a form of regularization and is also referred to in the statistics literature as the method of ‘supervised principal components’, see Bair et al. (2006).”
Ultrahigh dimensional feature selection: beyond the linear model (2009, methodology): “The method can be derived from an empirical likelihood point of view (Hall et al., 2009) and is related to supervised principal component analysis (Bair et al., 2006; Paul et al., 2008).”
High Dimensional Classification Using Features Annealed Independence Rules. (2007, methodology): “See, for example, principal component analysis in Ghosh (2002), Zou, Hastie and Tibshirani (2004) and Bair et al. (2006); partial least squares in Nguyen and Rocke (2002), Huang and Pan (2003) and Boulesteix (2004); and sliced inverse regression in Chiaromonte and Martinelli (2002), Antoniadis,…”
Supervised probabilistic principal component analysis (2006, background): “Other related works include [9, 12, 7, 1, 19, 20] which consider this problem from different perspectives.”
Sparse Multivariate Regression With Covariance Estimation (2010, methodology): “Another less directly relevant example of such supervised estimation is the supervised principal components by Bair et al. (2006).”
The Dantzig Selector in Cox's Proportional Hazards Model (2009, positive): “Following Bair et al. (2006), the covariate data are distributed as: log(Zij)= ⎧⎨ ⎩ 3+ ij if i ≤n/2, j ≤30 4+ ij if i > n/2, j ≤30 3.4+ ij if j > 30, where the ij are drawn from a standard normal distribution.”
A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data (2015, methodology): “PCA and many variations of it have been applied as a way of reducing the dimensionality of the data in cancer microarray data [58–64].”
Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds (2011, methodology): “[21] known as supervised principal components (in this paper, we refer to this method as Bair’s SPC).”
Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer's disease (2010, background): “There exist few supervised versions of singular value decomposition (SVD) and independent component analysis (ICA, e.g. (Bair et al., 2006; Sakaguchi et al., 2002)) which consider the class labels during feature transformation.”
Sensitivity of PCA for traffic anomaly detection (2007, background): “Recent theoretical work [3] attempts to overcome this limitation in certain circumstances.”
A computational solution for bolstering reliability of epigenetic clocks: Implications for clinical trials and longitudinal tracking (2021, neutral): “12) 68,69 .”
Principal fitted components for dimension reduction in regression (2008, methodology): “This motivation is prevalent in the genomics literature (see, e.g., Bura and Pfeiffer, 2003, and Li and Li, 2004) and is an important ingredient in the method of supervised principal components by Bair et al. (2006).”
Forecasting economic time series using targeted predictors (2008, background): “Our implementation of hard thresholding is closest to Bair et al. (2006), who, like Boivin and Ng (2006), also suggested that the principal components estimated from a large group of variables (which in their analysis are genes) can be dominated by principal components estimated from a smaller set o”
Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks (2020, background): “5 years)? What rate will they die or fail? It is a very important clinical application and many efforts have been made to search for biomarkers from omics data that are significantly related to patient death [1–5].”
Adaptive Lasso for sparse high-dimensional regression models (2008, background): “The partial orthogonality condition is reasonable in microarray data analysis, where the genes that are correlated with the phenotype of interest may be in different functional pathways from the genes that are not related to the phenotype (Bair et al. 2006).”