fdqcs.depth: Function to plot depth functional data (DFD) - chart

In mflores72000/qcr: Quality Control Review

Function to plot depth functional data (DFD) - chart

Description

This function is used to compute statistics required by the DFD chart.

Usage

fdqcs.depth(x, ...)

## Default S3 method:
fdqcs.depth(
  x,
  data.name = NULL,
  func.depth = depth.mode,
  nb = 200,
  type = c("trim", "pond"),
  ns = 0.01,
  plot = TRUE,
  trim = 0.025,
  smo = 0.05,
  draw.control = NULL,
  ...
)

## S3 method for class 'fdqcd'
fdqcs.depth(
  x,
  func.depth = depth.mode,
  nb = 200,
  type = c("trim", "pond"),
  ns = 0.01,
  plot = TRUE,
  trim = 0.025,
  smo = 0.05,
  draw.control = NULL,
  ...
)

Arguments

x	An object of class 'fdqcd'.
...	Arguments passed to or from methods.
data.name	A string that specifies the title displayed on the plots. If not provided it is taken from the name of the object x.
func.depth	Type of depth measure, by default depth.mode.
nb	The number of bootstrap samples.
type	The method used to trim the data (trim or pond).
ns	Quantile to determine the cutoff from the Bootstrap procedure.
plot	Logical value. If TRUE a DFD chart should be plotted.
trim	The percentage of the trimming.
smo	The smoothing parameter for the bootstrap samples.
draw.control	It specifies the col, lty and lwd for objects: fdataobj, statistic, IN and OUT.

References

Flores, M.; Naya, S.; Fernández-Casal,R.; Zaragoza, S.; Raña, P.; Tarrío-Saavedra, J. Constructing a Control Chart Using Functional Data. Mathematics 2020, 8, 58.

Examples

## Not run: 
library(qcr)
m <- 30
tt<-seq(0,1,len=m)
mu<-30 * tt * (1 - tt)^(3/2)
n0 <- 100
set.seed(12345)
mdata<-matrix(NA,ncol=m,nrow=n0)
sigma <- exp(-3*as.matrix(dist(tt))/0.9)
for (i in 1:n0) mdata[i,]<- mu+0.5*mvrnorm(mu = mu,Sigma = sigma )
fdchart <- fdqcd(mdata)
plot.fdqcd(fdchart,type="l",col="gray")
set.seed(1234)
fddep <- fdqcs.depth(fdchart,plot = T)
plot(fddep,title.fdata = "Fdata",title.depth = "Depth")
summary(fddep)

## End(Not run)

mflores72000/qcr documentation built on July 1, 2023, 9:17 p.m.