Functional linear discriminant analysis for irregularly sampled curves

By Gareth M. James, Trevor J. Hastie. 2001

342 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/d8acf000d86db3d47b08b40bfb86e84ec805dd0a

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

In Statistics and Probability

Citations in the corpus

Robust estimation and classification for functional data via projection-based depth notions (2007, methodology): “An extension of the classical linear discriminant analysis to the case of functional data has been considered in James and Hastie (2001) .”
Nonparametric Covariance Function Estimation for Functional and Longitudinal Data (2010, neutral): “Such a model is commonly adopted and suitable for a large number of applications in functional and longitudinal data analysis (see, e.g., Shi, Weiss and Taylor, 1996; Staniswalis and Lee, 1998; James and Hastie, 2001; Diggle et al., 2002; Müller, 2005; Ramsay and Silverman, 2005).”
Neural methods for non-standard data (2004, methodology): “Thus, linear techniques such as principal component analysis or linear discriminants and non-parametric models have been transferred to functional data [15, 22, 42 ].”
Achieving near perfect classification for functional data (2012, methodology): “In this case, this rule is also equivalent to the linear discriminant method studied by James and Hastie (2001) and Preda et al. (2007). The most interesting result is that when ∑ j≥1 θ −2 j μ 2 j = ∞, since this case exploits the functional nature of the data and can result in perfect classificatio”
Functional clustering and linear regression for peak load forecasting (2010, methodology): “In order to assign the new curves to clusters in the forecasting procedure, we use a functional linear discriminant analysis, as was done by James and Hastie (2001).”
Optimal estimation of the mean function based on discretely sampled functional data: Phase transition (2011, background): “Instead, each curve is discretely observed at a diﬀerent set of points [see, e.g., James and Hastie (2001), Rice and Wu (2001), Diggle et al. (2002), Yao, M¨uller and Wang (2005)].”
Curve alignment by moments (2007, methodology): “For example, functional principal components analysis [James, Hastie and Sugar (2000) and Rice and Wu (2001)], regression with both functional responses [Zeger and Diggle (1994)] and functional predictors [Ferraty and Vieu (2002) and James and Silverman (2005)], functional linear discriminant analys”
High-content flow cytometry and temporal data analysis for defining a cellular signature of graft-versus-host disease. (2007, background): “Recently, several algorithms treating time as a continuous variable have been introduced to deal with this issue, including spline-based methods such as linear, cubic and B-splines (21-29).”
Generalized linear models with functional predictors (2002, methodology): “Alternatively, Gao et al. (2001) model categorical responses using a combined smoothing spline analysis of variance and log-linear model approach, while James and Hastie (2001) use a functional linear discriminant analysis model.”
Classification Using Censored Functional Data (2013, methodology): “Therefore, as in James and Hastie (2001), our procedures are based on linear discriminant (LD) and quadratic discriminant (QD) classifiers.”
Functional Data Analysis (2016, methodology): “…X 0 is given by the Bayes formula, Developments along these lines include a functional linear discriminant analysis approach to classify curves (James & Hastie 2001), a functional data-analytic approach to signal discrimination, using the FPCA method for dimension reduction (Hall, Poskitt &…”
Functional Regression (2014, neutral): “The R package fpca implements the sparse PCA approaches of James, et al. (2000), and R and Matlab code for James and Hastie (2001) and FLiRTI (James, et al. 2009) are available at http://www-bcf.usc.edu/˜gareth/research/ Research.html.”
Clustering for Sparsely Sampled Functional Data (2003, methodology): “These data comprised four ethnic groups (black, Asian, white, and Hispanic), but the white and Hispanic groups were indistinguishable (James and Hastie 2001), so a three-cluster t may well correspond to the different ethnicities.”
Smoothing and mixed models (2003, methodology): “Other analyses are given in James, Hastie and Sugar (2000) and James and Hastie (2001) .”