CRAN Task View: Functional Data Analysis

Functional data analysis (FDA) deals with data that “provides information about curves, surfaces or anything else varying over a continuum.” This task view tries to provide an overview of available packages in this developing field.
In practice, there is substantial overlap between time series data and functional data, so many packages listed under the TimeSeries task view could be useful for functional data as well and vice versa.

General functional data analysis

• fda provides object-types for functional data with corresponding functions for smoothing, plotting and simple regression models, c.f. Ramsay et al. (2009, doi:10.1007/978-0-387-98185-7).
• fdasrvf performs alignment, PCA, and regression of multidimensional or unidimensional functions using the square-root velocity framework, c.f. Srivastava et al. (2011, doi:10.48550/arXiv.1103.3817). This framework allows for elastic analysis of functional data through phase and amplitude separation.
• fdapace provides functional principal component based methods for sparsely or densely sampled random trajectories and time courses for functional regression and correlation, for longitudinal data analysis, the analysis of stochastic processes from samples of realized trajectories, and for the analysis of underlying dynamics.
• fda.usc provides routines for exploratory and descriptive analysis of functional data such as depth measurements, outlier detection, as well as unsupervised and supervised classification, (univariate, nonparametric) regression models with a functional covariate and functional analysis of variance.
• fds contains 19 data sets with functional data.
• funData provides S4 classes for univariate and multivariate functional and image data and utility functions.
• rainbow contains functions and data sets for functional data display, exploratory analysis and outlier detection.
• fdaoutlier provides a collection of functions for functional data outlier detection. Methods implemented include directional outlyingness, MS-plot, total variation depth, and sequential transformations among others.

Regression and classification for functional data

• dbstats provides prediction methods where explanatory information is coded as a matrix of distances between individuals. It includes distance based versions of lm and glm, as well as nonparametric versions of both, based on local estimation. To apply these methods to functional data it is sufficient to calculate a distance matrix between the observed functional data.
• denseFLMM and sparseFLMM estimate functional linear mixed models for densely and sparsely sampled data, respectively, based on functional principal component analysis.
• fdANOVA implements analysis of variance testing procedures for univariate and multivariate functional data.
• fdaPDE implements statistical analysis of functional and spatial data over multidimensional complex domains, based on regression models with partial differential regularization, discretized through the finite element method.
• FDboost implements flexible additive regression models and variable selection for scalar-on-function, function-on-scalar and function-on-function regression models that are fitted by a component-wise gradient boosting algorithm.
• flars (archived) implements variable selection for the functional linear regression with scalar response variable and mixed scalar/functional predictors based on the least angle regression approach.
• GPFDA uses functional regression as the mean structure and Gaussian processes as the covariance structure.
• growfunctions estimates a collection of time-indexed functions under either of Gaussian process (GP) or intrinsic Gaussian Markov random field (iGMRF) prior formulations where a Dirichlet process mixture allows sub-groupings of the functions to share the same covariance or precision parameters. The GP and iGMRF formulations both support any number of additive covariance or precision terms, respectively, expressing either or both of multiple trend and seasonality.
• multifamm implements multivariate functional additive mixed models (multiFAMM) based on univariate sparse functional regression models and multivariate functional principal component analysis, c.f. Volkmann et al. (2012, doi:10.48550/arXiv.2103.06606).
• refund provides spline-based methods for roughness penalized function-on-scalar, scalar-on-function, and function-on-function regression as well as methods for functional PCA. Some of the functions are also applicable to image data.
• splinetree implements regression trees and random forests for longitudinal or functional data using a spline projection method.

Clustering functional data

• funFEM ’s algorithm (Bouveyron et al., 2014) allows to cluster functional data by modeling the curves within a common and discriminative functional subspace.
• funHDDC provides the funHDDC algorithm (Bouveyron & Jacques, 2011) which allows to cluster functional data by modeling each group within a specific functional subspace.
• funLBM implements model-based co-clustering of functional data, i.e., simultaneously clustering the rows and the columns of a data matrix where each entry of the matrix is a function or a time series.
• fdakma (archived) performs clustering and alignment of a multidimensional or unidimensional functional dataset by means of k-mean alignment.

Registering and aligning functional data

• elasdics provides functions to align curves and to compute mean curves based on the elastic distance defined in the square-root-velocity framework, c.f. Steyer et al. (2021, doi:10.48550/arXiv.2104.11039).
• fdasrvf performs alignment, PCA, and regression of multidimensional or unidimensional functions using the square-root velocity framework (Srivastava et al., 2011). This framework allows for elastic analysis of functional data through phase and amplitude separation.
• fdakma (archived) performs clustering and alignment of a multidimensional or unidimensional functional dataset by means of k-mean alignment.
• registr provides registration for (incomplete) non-Gaussian functional data, c.f Wrobel et al. (2019, doi:10.1111/biom.12963), Wrobel and Bauer (2021, doi:10.21105/joss.02964).
• warpMix implements warping (alignment) for functional data using B-spline based mixed effects models.

Time series of functional data

• ftsa provides functions for visualizing, modeling, forecasting and hypothesis testing of functional time series.
• ftsspec provides functions for estimating the spectral density operator of functional time series (FTS) and comparing the spectral density operator of two functional time series, in a way that allows detection of differences of the spectral density operator in frequencies and along the curve length.
• freqdom provides frequency domain methods for multivariate and functional time series and implements dynamic functional principal components and functional regression in the presence of temporal dependence.
• freqdom.fda provides a wrapper for functionality of freqdom for objects from fda
• pcdpca extends multivariate dynamic principal components to periodically correlated multivariate and functional time series.
• fdaACF contains functions to quantify the serial correlation across lags of a given functional time series, see also github.com/GMestreM/fdaACF .

Other

• covsep provides functions for testing if the covariance structure of 2-dimensional data is separable.
• ddalpha implements depth-based classification and calculation of data depth, also for functional data.
• face implements Fast Covariance Estimation for Sparse Functional Data, c.f. Xiao et al. (2018, doi:10.1007/s11222-017-9744-8).
• fdadensity implements Petersen and Müller (2016, doi:10.1214/15-AOS1363) for the analysis of samples of density functions via specialized Functional Principal Components Analysis.
• fdatest provides an implementation of the Interval Testing Procedure for functional data in different frameworks (i.e., one or two-population frameworks, functional linear models) by means of different basis expansions (i.e., B-spline, Fourier, and phase-amplitude Fourier).
• fdcov (archived) provides a variety of tools for the analysis of covariance operators.
• frechet implements Fréchet regression for for non-Euclidean responses, e.g. distributions in L^2-Wasserstein space or covariance matrices, c.f. Petersen & Müller (2019, doi:10.1214/17-AOS1624).
• geofd provides Kriging based methods for predicting functional data (curves) with spatial dependence.
• mfaces implements multivariate functional principal component analysis via fast covariance estimation for multivariate sparse functional data or longitudinal data, c.f Li, Xiao, and Luo (2020, doi:10.1002/sta4.245)
• MFPCA calculates multivariate FPCA for “multimodal” data observed on domains with different dimensionalities, c.f. Happ and Greven (2018, doi:10.1080/01621459.2016.1273115).
• SCBmeanfd provides methods for estimating and inferring the mean of functional data. The methods include simultaneous confidence bands, local polynomial fitting, bandwidth selection by plug-in and cross-validation, goodness-of-fit tests for parametric models, equality tests for two-sample problems, and plotting functions.

Please e-mail the maintainer with suggestions, additions, and improvements or submit an issue or pull request in the GitHub repository linked above.

CRAN packages

Related links

• Website of the canonical FDA book by Ramsay and Silverman
• PACE: collection of MATLAB scripts from UC Davis
• WFMM: powerful software for Bayesian wavelet-based functional mixed models (C++/Matlab)
• scikit-FDA: comprehensive Python package for FDA

Other resources

• CRAN Task View: TimeSeries