Fréchet integration and adaptive metric selection for interpretable covariances of multivariate functional data

  title={Fr{\'e}chet integration and adaptive metric selection for interpretable covariances of multivariate functional data},
  author={Alexander Petersen and Hans-Georg M{\"u}ller},
For multivariate functional data recorded from a sample of subjects on a common domain, one is often interested in the covariance between pairs of the component functions, extending the notion of a covariance matrix for multivariate data to the functional case. A straightforward approach is to integrate the pointwise covariance matrices over the functional time domain. We generalize this approach by defining the Frechet integral, which depends on the metric chosen for the space of covariance… 

Figures and Tables from this paper

Total Variation Regularized Fréchet Regression for Metric-Space Valued Data
Non-Euclidean data that are indexed with a scalar predictor such as time are increasingly encountered in data applications, while statistical methodology and theory for such random objects are not
Functional models for time‐varying random objects
  • P. Dubey, H. Müller
  • Mathematics
    Journal of the Royal Statistical Society: Series B (Statistical Methodology)
  • 2020
Functional data analysis provides a popular toolbox of functional models for the analysis of samples of random functions that are real valued. In recent years, samples of time‐varying object data
Dynamic Network Regression
This work proposes to adopt conditional Fréchet means implemented with both global least squares regression and local weighted least squares smoothing, extending the FrÉchet regression concept to networks that are quantified by their graph Laplacians.
Inference for the Lagged Cross‐Covariance Operator Between Functional Time Series
When considering two or more time series of functional data objects, for instance those derived from densely observed intraday stock price data of several companies, the empirical cross‐covariance
Fréchet estimation of time-varying covariance matrices from sparse data, with application to the regional co-evolution of myelination in the developing brain
A Fr\'echet estimation method where data per subject are limited to measurements taken at only one random age, while aiming at the time-varying dynamics, and generates a matrix function where at each time the matrix is a non-negative definite covariance matrix, for which it is demonstrated consistency properties.
Fast covariance estimation for multivariate sparse functional data
A fast covariance estimation method for multivariate sparse functional data using bivariate penalized splines and a fast algorithm for selecting the smoothing parameters in covariance smoothing using leave-one-subject-out cross-validation is derived.
Dynamic Functional Connectivity Change-Point Detection With Random Matrix Theory Inference
The study shows the possibility of RMT based approach in DFC change-point problem and in studying the complex dynamic pattern of functional brain interactions by applying the method to epilepsy data where change-points detected are explained by the changes in memory capacity.
Change-Point Estimation and Testing for Brain Functional Connectivity Networks
  • Jaehee Kim
  • Biology
    2019 11th International Conference on Knowledge and Smart Technology (KST)
  • 2019
This work develops a method that leverages the entire covariance matrix, enabling relatively fast and efficient change-point estimation in dynamic FC and incorporates multivariate time series imaging data, reflecting spatial correlations between distinct brain regions.
Spatial modeling of Object Data: Analysing dialect sound variations across the UK
This work introduces novel statistical techniques to analyse geolocalised speech recordings and to explore the spatial variation of pronunciations continuously over the region of interest, as opposed to traditional isoglosses, which provide a discrete partition of the region.
Variable Selection for Global Fréchet Regression
Global Frechet regression is an extension of linear regression to cover more general types of responses, such as distributions, networks and manifolds, which are becoming more prevalent. In such mo...


Distances and inference for covariance operators
A framework is developed for inference concerning the covariance operator of a functional random process, where the covariance operator itself is an object of interest for statistical analysis.
Functional singular component analysis
Summary.  Aiming at quantifying the dependence of pairs of functional data (X,Y), we develop the concept of functional singular value decomposition for covariance and functional singular component
Multivariate functional principal component analysis: A normalization approach
This study proposes a modified version of the classical Karhunen-Loeve expansion for a vector-valued random process, called a normalized multivariate functional principal component (mFPCn) approach,
Dynamical Correlation for Multivariate Longitudinal Data
Nonparametric methodology for longitudinal data analysis is becoming increasingly popular. The analysis of multivariate longitudinal data, where data on several time courses are recorded for each
Canonical correlation analysis when the data are curves.
SUMMARY It is not immediately straightforward to extend canonical correlation analysis to the context of functional data analysis, where the data are themselves curves or functions. The obvious
Functional projection pursuit regression
In this paper we introduce a flexible approach to approximate the regression function in the case of a functional predictor and a scalar response. Following the Projection Pursuit Regression
Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
The statistical analysis of covariance matrices occurs in m any important applications, e.g. in diffusion tensor imaging or longitudinal data analysis. We consider the situation where it is of
Spearman coefficient for functions
We present a notion of Spearman's coefficient for functional data that extends the classical bivariate concept to situations where the observed data are curves generated by a stochastic process.