Regularized linear discriminant analysis and its application in microarrays.

By Yaqian Guo, Trevor J. Hastie, Robert Tibshirani. Biostatistics, 2007

636 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/64542bb7091d9574cb19e17c123b9236fad91d8b

How researchers see this paper

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

In Analytical Chemistry

1. Kjell Johnson
2. Daniela M. Witten
3. Max Kuhn
4. Alaa Tharwat
5. Johanna S. Hardin
6. David Golan
7. Stephan Ramon Garcia
8. Pascal G. P. Martin

In Molecular Biology

1. Kjell Johnson
2. Max Kuhn
3. Daniela M. Witten
4. Robert Tibshirani
5. Alaa Tharwat
6. Adi L. Tarca
7. Rok Blagus
8. Lara Lusa

Citations in the corpus

• Machine Learning and Its Applications to Biology (2007, background): “In very recent work, Guo and colleagues [17] have presented a regularized linear discriminant analysis procedure useful when the number of features far exceeds the number of samples.”
• Penalized classification using Fisher’s linear discriminant (2011, methodology): “…years, a number of authors have proposed extensions of LDA to the high-dimensional setting in order to achieve sparsity (Tibshirani et al., 2002, 2003; Guo et al., 2007; Trendafilov and Jolliffe, 2007; Grosenick et al., 2008; Leng, 2008; Fan and Fan, 2008; Shao et al., 2011; Clemmensen et al., 2011).”
• SMOTE for high-dimensional class-imbalanced data (2013, background): “2 or 0 (independence case), while the variables from different blocks were independent [38].”
• Linear vs. quadratic discriminant analysis classifier: a tutorial (2016, methodology): “, two classes ωi and ωj, and it consists of two discriminant functions, fi and fj (Hastie et al., 2001; Guo et al., 2007; Duda et al., 2012; Fukunaga, 2013).”
• A method for generating realistic correlation matrices (2011, methodology): “The Toeplitz structure has been used extensively in classification and dis-254 criminant analysis as a model for group correlations [7,9,34,41,45].”
• Applied Predictive Modeling (2013, methodology): “The nearest-shrunken centroid model (also known as PAM, for predictive analysis for microarrays) is a linear classification model that is well suited for high-dimensional problems (Tibshirani et al. 2002, 2003; Guo et al. 2007).”
• CCA: An R Package to Extend Canonical Correlation Analysis (2008, background): “An alternative consists in building a relatively small grid of “reasonable” values for λ1 and λ2, to evaluate the cross validation score at each point of the grid, and then to choose the value of λ = (λ1, λ2) that gives the largest CV -score (Friedman 1989; Guo et al. 2007).”