genModelFD {TFunHDDC} | R Documentation |
genModelFD
Description
Generate functional data with coefficients distributed according to a finite mixture of contamined normal distributions such that for the th cluster we have the
multivariate contaminated normal distribution with density
where represents the proportion of uncontaminated data,
is the inflation coefficient due to outliers, and
is the density for the multivariate normal distribution
.
Usage
genModelFD(ncurves=1000, nsplines=35, alpha=c(0.9,0.9,0.9),
eta=c(10, 5, 15))
Arguments
ncurves |
The number of curves total for the simulation. |
nsplines |
The number of splines to fit to the simulated data. |
alpha |
The proportion of uncontaminated data in each group. |
eta |
The inflation coefficient that measures the increase in variability due to the outliers. |
Details
The data are generate from the model .
The number of clusters is fixed to
and the mixing proportions are equal
. We consider the following values of the parameters
Group 1:,
,
,
Group 2: ,
,
,
Group 3: ,
,
,
,
where is the intrinsic dimension of the subgroups,
is the mean vector of size 70,
is the values of the
-first diagonal elements of
, and
the value of the last
- elements. Curves as smoothed using 35 Fourier basis functions.
Value
fd |
A functional data object representing the simulated data. |
groupd |
Group classifications for each curve. |
Author(s)
Cristina Anton and Iain Smith
References
- Amovin-Assagba M, Gannaz I, Jacques J (2022) Outlier detection in multivariate
functional data through a contaminated mixture model. Comput Stat
Data Anal 174.
- Cristina Anton, Iain Smith Model-based clustering of functional data via mixtures of distributions. Advances in Data Analysis and Classification (to appear).
Examples
# Univariate Contaminated Data
data <- genModelFD(ncurves=300, nsplines=35, alpha=c(0.9,0.9,0.9),
eta=c(10, 7, 17))
plot(data$fd, col = data$groupd)
clm <- data$groupd