Defining probability density for a distribution of random functions

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.

Published in at http://dx.doi.org/10.1214/09-AOS741 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (1)

• Defining probability density for a distribution of random functions

Cited by in corpus (14)

• Defining probability density for a distribution of random functions
• Review of Functional Data Analysis
• Optimal Bayes Classifiers for Functional Data and Density Ratios
• Classification methods for Hilbert data based on surrogate density
• Consistency of the mean and the principal components of spatially distributed functional data
• Clustering multivariate functional data using unsupervised binary trees
• Bi-Smoothed Functional Independent Component Analysis for EEG Artifact Removal
• Nonparametric Hierarchical Clustering of Functional Data
• Nonparametric Clustering of Functional Data Using Pseudo-Densities
• Formal Privacy for Functional Data with Gaussian Perturbations
• Distance for Functional Data Clustering Based on Smoothing Parameter Commutation
• Sparse Functional Linear Discriminant Analysis
• Functional Data Analysis with Causation in Observational Studies: Covariate Balancing Functional Propensity Score for Functional Treatments
• Simulating signed mixtures