Theoretical Measures of Relative Performance of Classifiers for High Dimensional Data with Small Sample Sizes

DOI10.1111/j.1467-9868.2007.00631.xzbMath1400.62094OpenAlexW1587510588WikidataQ94319350 ScholiaQ94319350MaRDI QIDQ3631449

Hall, Peter, Malay Ghosh, Y. E. Pittelkow

Publication date: 10 June 2009

Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/1885/37045

zbMATH Keywords

truncationthresholdingdetectionsparsityhigher criticismsupport vector machineclassification boundarynearest neighbour methoddistance-weighted discriminationdistance-based classification

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20)

Related Items

Optimal properties of centroid-based classifiers for very high-dimensional data, A classifier under the strongly spiked eigenvalue model in high-dimension, low-sample-size context, A \(U\)-classifier for high-dimensional data under non-normality, Unnamed Item, Robust support vector machine for high-dimensional imbalanced data, The intermediates take it all: Asymptotics of higher criticism statistics and a powerful alternative based on equal local levels, Support vector machine and its bias correction in high-dimension, low-sample-size settings, Optimal classification in sparse Gaussian graphic model, Detectability of nonparametric signals: higher criticism versus likelihood ratio, A survey of high dimension low sample size asymptotics, Classification of sparse high-dimensional vectors, Properties of higher criticism under strong dependence, Distance-based classifier by data transformation for high-dimension, strongly spiked eigenvalue models, Innovated higher criticism for detecting sparse signals in correlated noise, Bias-corrected support vector machine with Gaussian kernel in high-dimension, low-sample-size settings, Thresholding-based outlier detection for high-dimensional data, A distance-based, misclassification rate adjusted classifier for multiclass, high-dimensional data, Asymptotic properties of distance-weighted discrimination and its bias correction for high-dimension, low-sample-size data, Two-Stage Procedures for High-Dimensional Data, Optimal Detection of Heterogeneous and Heteroscedastic Mixtures, Signal detection via Phi-divergences for general mixtures, Robust nearest-neighbor methods for classifying high-dimensional data, Higher criticism for large-scale inference, especially for rare and weak effects

Cites Work

• Estimating the proportion of false null hypotheses among a large number of independently tested hypotheses
• Subsampling for heteroskedastic time series
• On the distribution of the largest eigenvalue in principal components analysis
• Adaptive detection of a signal of growing dimension. I
• Adaptive detection of a signal of growing dimension. II
• Higher criticism for detecting sparse heterogeneous mixtures.
• Cosmological non-Gaussian signature detection: comparing performance of different statistical tests
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Geometric Representation of High Dimension, Low Sample Size Data
• Large-Scale Simultaneous Hypothesis Testing
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item