stepArchetypesRawData_robust: Archetype algorithm to raw data with the robust Frobenius norm

Description

This is a slight modification of stepArchetypesRawData to use the archetype algorithm with the robust Frobenius norm.

Usage

stepArchetypesRawData_robust(data, numArch, numRep = 3, 
                             verbose = TRUE, saveHistory = FALSE, prob)

Arguments

data

Data to obtain archetypes.

numArch

Number of archetypes to compute, from 1 to numArch.

numRep

For each numArch, run the archetype algorithm numRep times.

verbose

If TRUE, the progress during execution is shown.

saveHistory

Save execution steps.

prob

Probability with values in [0,1].

Value

A list with the archetypes.

References

Moliner, J. and Epifanio, I., Robust multivariate and functional archetypal analysis with application to financial time series analysis, 2019. Physica A: Statistical Mechanics and its Applications 519, 195-208. https://doi.org/10.1016/j.physa.2018.12.036

Examples

Run this code

# NOT RUN {
data(mtcars)
data <- as.matrix(mtcars)

numArch <- 5 
numRep <- 2

lass <- stepArchetypesRawData_robust(data = data, numArch = 1:numArch, 
                                     numRep = numRep, verbose = FALSE,
                                     saveHistory = FALSE, prob = 0.8)
str(lass)   
length(lass[[1]])
class(lass[[1]])                                       
                 
# }