The goal of package newIMVC is to provide an easy way to
implement the proposed methods in Xiong et al. (2024), which include a
new robust correlation between continuous variables and its use in
hypothesis test, feature screening and false discovery rate control.
Here are examples showing how to use main functions in package
newIMVC.
library("newIMVC")
library("mvtnorm")
#> Warning: package 'mvtnorm' was built under R version 4.3.3
###The new IMVC measure###
n=200
x=rnorm(n)
y=x^2+rt(n,2)
IMVC(y,x,K=10,type="nonlinear")
#> [1] 0.2225841
###IMVC based feature screening###
n=200
p=300
pho1=0.8
mean_x=rep(0,p)
sigma_x=matrix(NA,nrow = p,ncol = p)
for (i in 1:p) {
for (j in 1:p) {
sigma_x[i,j]=pho1^(abs(i-j))
}
}
x=rmvnorm(n, mean = mean_x, sigma = sigma_x,method = "chol")
x1=x[,1]
x2=x[,2]
x3=x[,12]
x4=x[,22]
y=2*x1+0.5*x2+3*x3*ifelse(x3<0,1,0)+2*x4+rnorm(n)
IMVCS(y,x,K=5,d=round(n/log(n)),type="nonlinear")
#> [1] 1 2 22 3 4 23 12 21 13 5 14 11 15 24 6 7 25 8 9
#> [20] 20 10 104 19 16 212 224 156 39 17 168 18 175 103 226 119 128 227 218
###IMVC based hypothesis test###
n=100
x=rnorm(n)
y=2*x+rt(n,2)
IMVCT(x,y,K=5,type = "linear")
#> [1] 1.506868e-16
y=2*cos(x)+rt(n,2)
IMVCT(x,y,K=5,type = "nonlinear",num_per = 100)
#> [1] 0
###IMVC based FDR control###
n=200
p=100
pho1=0.5
mean_x=rep(0,p)
sigma_x=matrix(NA,nrow = p,ncol = p)
for (i in 1:p) {
for (j in 1:p) {
sigma_x[i,j]=pho1^(abs(i-j))
}
}
x=rmvnorm(n, mean = mean_x, sigma = sigma_x,method = "chol")
x1=x[,1]
x2=x[,2]
x3=x[,3]
x4=x[,4]
x5=x[,5]
y=x1+x2+x3+x4+x5+rnorm(n)
IMVCFDR(y,x,K=5,numboot=100,timeboot=50,true_signal=c(1,2,3,4,5),null_method="hist",alpha=0.2)
#> $selected
#> [1] 3 5 4 2 6
#>
#> $FDR
#> [1] 0.2
#>
#> $Power
#> [1] 0.8Wei Xiong, Han Pan, Hengjian Cui. (2024) “A Robust Integrated Mean Variance Correlation and Its Use in High Dimensional Data Analysis.”