Defining probability density for a distribution of random functions

DOI10.1214/09-AOS741zbMATH Open1183.62061arXiv1002.4931OpenAlexW2091910201MaRDI QIDQ2380100FDOQ2380100

Authors: Aurore Delaigle, Peter Hall 

Publication date: 24 March 2010

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: The notion of probability density for a random function is not as straightforward as in finite-dimensional cases. While a probability density function generally does not exist for functional data, we show that it is possible to develop the notion of density when functional data are considered in the space determined by the eigenfunctions of principal component analysis. This leads to a transparent and meaningful surrogate for density defined in terms of the average value of the logarithms of the densities of the distributions of principal components for a given dimension. This density approximation is estimable readily from data. It accurately represents, in a monotone way, key features of small-ball approximations to density. Our results on estimators of the densities of principal component scores are also of independent interest; they reveal interesting shape differences that have not previously been considered. The statistical implications of these results and properties are identified and discussed, and practical ramifications are illustrated in numerical work.

Full work available at URL: https://arxiv.org/abs/1002.4931

Recommendations

• Nonparametric estimation of a surrogate density function in infinite-dimensional spaces
• Kernel spatial density estimation in infinite dimension space
• Nonparametric density estimation for functional data via wavelets
• Analysis of kernel density estimation of functions of random variables
• scientific article; zbMATH DE number 3928098

zbMATH Keywords

density estimationfunctional data analysiskernel methodsnonparametric statisticsprincipal components analysisprobability density functioneigenfunctioneigenvaluedimensionscale spacelog-density estimationresolution levelAustralian rainfall data

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Density estimation (62G07) Factor analysis and principal components; correspondence analysis (62H25)

Cites Work

• Title not available (Why is that?)
• SiZer for Exploration of Structures in Curves
• Functional data analysis.
• Nonparametric functional data analysis. Theory and practice.
• Title not available (Why is that?)
• Nonparametric regression for mixing functional random variables
• Applied functional data analysis. Methods and case studies
• Robust functional estimation using the median and spherical principal components
• Title not available (Why is that?)
• Title not available (Why is that?)
• On Properties of Functional Principal Components Analysis
• Curves discrimination: a nonparametric functional approach
• How many principal components? Stopping rules for determining the number of non-trivial axes revisited
• Principal components analysis of sampled functions
• Determining the number of components from the matrix of partial correlations
• A rationale and test for the number of factors in factor analysis
• Title not available (Why is that?)
• Scale space view of curve estimation.
• Smoothed functional principal components analysis by choice of norm
• Defining probability density for a distribution of random functions
• Functional Nonparametric Statistics in Action
• The functional nonparametric model and applications to spectrometric data
• Functional nonparametric model for time series: a fractal approach for dimension reduction
• Theory for high-order bounds in functional principal components analysis
• Nonparametric Estimation of the Mode of A Distribution of Random Curves
• Nonparametric models for functional data, with application in regression, time series prediction and curve discrimination
• Assessing the Finite Dimensionality of Functional Data
• On the using of modal curves for radar waveforms classification
• Estimating and depicting the structure of a distribution of random functions
• Mode estimation for functional random variable and its application for curves classification
• Density estimation in an infinite dimensional space: Application to diffusion processes
• THE MODE AND MEDIAN OF A NEARLY NORMAL DISTRIBUTION WITH GIVEN CUMULANTS
• On the limiting behaviour of the mode and median of a sum of independent random variables
• Mode estimation in a semi-normed vectorial space.

Cited In (51)

• On the definition of phase and amplitude variability in functional data analysis
• A survey on model-based co-clustering: high dimension and estimation challenges
• Functional data clustering via information maximization
• Functional data clustering using principal curve methods
• The naive Bayes classifier for functional data
• Functional data clustering: a survey
• Adaptive and minimax estimation of the cumulative distribution function given a functional covariate
• Model-based clustering for multivariate functional data
• Mixture inner product spaces and their application to functional data analysis
• Classification methods for Hilbert data based on surrogate density
• Copula-Based Functional Bayes Classification With Principal Components and Partial Least Squares
• Dynamic quantile function models
• Outlier detection in multivariate functional data through a contaminated mixture model
• Covariate balancing functional propensity score for functional treatments in cross-sectional observational studies
• Classification of social media users with generalized functional data analysis
• Minimax estimation of the mode of functional data
• Evaluating the complexity of some families of functional data
• Functional principal subspace sampling for large scale functional data analysis
• Simultaneous Registration and Clustering for Multidimensional Functional Data
• Using pseudometrics in kernel density estimation
• Defining probability density for a distribution of random functions
• Variable selection in partial linear regression with functional covariate
• Optimal classification of Gaussian processes in homo- and heteroscedastic settings
• On a nonlinear extension of the principal fitted component model
• Deriving a probability density calculator (functional pearl)
• Functional data clustering via piecewise constant nonparametric density estimation
• The Statistical Face of a Region Under Monsoon Rainfall in Eastern India
• Lower bound in regression for functional data by representation of small ball probabilities
• Nested nonnegative cone analysis
• Model-based clustering of time series in group-specific functional subspaces
• Consistency of \(h\)-mode depth
• Robust clustering for functional data based on trimming and constraints
• Nonparametric density estimation for intentionally corrupted functional data
• A joint latent factor analyzer and functional subspace model for clustering multivariate functional data
• Co-clustering of multivariate functional data for the analysis of air pollution in the south of France
• A partial overview of the theory of statistics with functional data
• PCA-kernel estimation
• Quantifying the closeness to a set of random curves via the mean marginal likelihood
• Functional boxplots based on epigraphs and hypographs
• Bayesian optimization of functional output in inverse problems
• Smooth neighborhood recommender systems
• Clustering multivariate functional data using unsupervised binary trees
• Empirical evolution equations
• Nonparametric estimation of a surrogate density function in infinite-dimensional spaces
• The correction term in a small-ball probability factorization for random curves
• Pseudo-quantile functional data clustering
• Nonparametric modelling for functional data: selected survey and tracks for future
• Smoothed functional canonical correlation analysis of humidity and temperature data
• Uncertainty quantification for functional dependent random variables
• Multivariate functional data clustering using adaptive density peak detection
• Model-based clustering of functional data via mixtures of \(t\) distributions

Uses Software

• fda (R)
• KernSmooth
• SiZer

This page was built for publication: Defining probability density for a distribution of random functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2380100)