Learn R Programming

fda.usc: Functional Data Analysis and Utilities for Statistical Computing

Package overview

fda.usc package carries out exploratory and descriptive analysis of functional data exploring its most important features such as depth measurements or functional outliers detection, among others. It also helps to explain and model the relationship between a dependent variable and independent (regression models) and make predictions. Methods for supervised or unsupervised classification of a set of functional data regarding a feature of the data are also included. It can perform functional ANOVA, hypothesis testing, functional response models and many others.

Installation

You can install the current fda.usc version from CRAN with:

install.packages("fda.usc")

or the latest patched version from Github with:

library(devtools)
devtools::install_github("moviedo5/fda.usc")

Issues & Feature Requests

For issues, bugs, feature requests etc. please use the Github Issues. Input is always welcome.

Documentation

A hands on introduction to can be found in the reference vignette.

Details on specific functions are in the reference manual.

Cheatsheet fda.usc reference card.

References

Febrero-Bande, M. and Oviedo de la Fuente, M. (2012). Statistical Computing in Functional Data Analysis: The R Package fda.usc. Journal of Statistical Software, 51(4):1-28. https://dx.doi.org/10.18637/jss.v051.i04

Copy Link

Version

Install

install.packages('fda.usc')

Monthly Downloads

1,837

Version

2.1.0

License

GPL-2

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/moviedo5/fda.usc

Homepage

https://www.jstatsoft.org/v51/i04/

Maintainer

Manuel Oviedo de la Fuente

Last Published

October 17th, 2022

Functions in fda.usc (2.1.0)

False Discorvery Rate (FDR)

The generalized correlated cross-validation (GCCV) score

Descriptive measures for functional data.

Symmetric Smoothing Kernels.

Kernel.asymmetric

Asymmetric Smoothing Kernel

Mithochondiral calcium overload (MCO) data set

Kernel.integrate

Integrate Smoothing Kernels.

Impact points selection of functional predictor and regression using local maxima distance correlation (LMDC)

Performance measures for regression and classification models

Sampling Variance estimates

The cross-validation (CV) score

The generalized correlated cross-validation (GCCV) score.

Penalty matrix for higher order differences

Classification Fitting Functional Generalized Linear Models

outliers for functional dataset

Classification Fitting Functional Generalized Kernel Additive Models

Smoothing matrix by nonparametric methods

Smoothing matrix with roughness penalties by basis representation.

Classifier from Functional Data

Classification Fitting Functional Generalized Additive Models

Functional classification using ML algotithms

Functional Classification usign k-fold CV

Kernel Classifier from Functional Data

DD-Classifier Based on DD-plot

classif.gsam.vs

Variable Selection in Functional Data Classification

create.fdata.basis

Create Basis Set for Functional Data of fdata class

Provides the depth measure for multivariate data

Conditional mode

fEqMoments.test

Tests for checking the equality of means and/or covariance between two populations under gaussianity.

Computation of depth measures for functional data

PCvM statistic for the Functional Linear Model with scalar response

fEqDistrib.test

Tests for checking the equality of distributions between two functional populations.

Provides the depth measure for a list of p--functional data objects

Proximities between functional data

Delsol, Ferraty and Vieu test for no functional-scalar interaction

Conditional quantile

Conditional Distribution Function

Distance Correlation Statistic and t-Test

fanova.onefactor

One--way anova model for functional data

Functional data centred (subtract the mean of each discretization point)

fregre.bootstrap

Bootstrap regression

fregre.basis.cv

Cross-validation Functional Regression with scalar response using basis representation.

Converts raw data or other functional data classes into fdata class.

fdata.bootstrap

Bootstrap samples of a functional statistic

The deviance score

Goodness-of-fit test for the Functional Linear Model with scalar response

ANOVA for heteroscedastic data

fregre.basis.fr

Functional Regression with functional response using basis representation.

Principal components for functional data

Converts fdata class object into fd class object

fda.usc-package

Functional Data Analysis and Utilities for Statistical Computing (fda.usc)

fdata S3 Group Generic Functions

Functional ANOVA with Random Project.

Cross-validation functional regression with scalar response using kernel estimation.

Functional regression with scalar response using non-parametric kernel estimation

Fitting Functional Generalized Kernel Additive Models.

Computes the derivative of functional data object.

Functional Regression with scalar response using basis representation.

Partial least squares components for functional data.

F-test for the Functional Linear Model with scalar response

Variable Selection using Functional Linear Models

Fitting Functional Linear Models

influence.fregre.fd

Functional influence measures

Inner products of Functional Data Objects o class (fdata)

Fitting Functional Generalized Spectral Additive Models

Compute fucntional coefficients from functional data represented in a base of functions

fda.usc.internal

fda.usc internal functions

mfdata class definition and utilities

ldata class definition and utilities

Calculation of the smoothing parameter (h) for a functional data

Simpson integration

Fitting Functional Generalized Linear Models

Fit of Functional Generalized Least Squares Model Iteratively

Fit Functional Linear Model Using Generalized Least Squares

ops.fda.usc Options Settings

metric.hausdorff

Compute the Hausdorff distances between two curves.

Variable Selection using Functional Additive Models

predict.fregre.fd

Predict method for functional linear model (fregre.fd class)

Functional Regression with scalar response using Principal Components Analysis

Quantile for influence measures

Functional penalized PLS regression with scalar response using selection of number of PLS components

Functional penalized PC regression with scalar response using selection of number of PC components

rp.flm.statistic

Statistics for testing the functional linear model using random projections

Data-driven sampling of random directions guided by sample of functional data

Semi-functional partially linear model with scalar response.

Approximates Lp-metric distances for functional data.

Kullback--Leibler distance

Plot functional data: fdata class object

Goodness-of fit test for the functional linear model using random projections

Ornstein-Uhlenbeck process

A wrapper for the na.omit and na.fail function for fdata object

predict.classif.DD

Predicts from a fitted classif.DD object.

kmeans.center.ini

K-Means Clustering for functional data

predict.fregre.fr

Predict method for functional response model

Functional Penalized PLS regression with scalar response

Weighting tools

predict.fregre.gkam

Predict method for functional linear model

semimetric.NPFDA

Proximities between functional data (semi-metrics)

Smoothing of functional data using nonparametric kernel estimation

summary.fregre.fd

Summarizes information from fregre.fd objects.

predict.classif

Predicts from a fitted classif object.

predict.fregre.gls

Predictions from a functional gls object

semimetric.basis

Proximities between functional data

summary.fdata.comp

Correlation for functional data by Principal Component Analysis

Select the number of basis using GCV method.

Approximates Lp-norm for functional data.

Simulate several random processes.

Distance Matrix Computation for ldata and mfdata class object

summary.classif

Summarizes information from kernel classification methods.

Distance Matrix Computation

Wild bootstrap residuals

Utils for generate functional data

summary.fregre.gkam

Summarizes information from fregre.gkam objects.

DTW: Dynamic time warping