MVSIS: Model-Free Feature Screening for Ultrahigh Dimensional...

In MFSIS: Model-Free Sure Independent Screening Procedures

Model-Free Feature Screening for Ultrahigh Dimensional Discriminant Analysis

Description

A marginal feature screening procedure based on empirical conditional distribution function. The response variable is categorical in discriminant analysis. This enables us to use the conditional distribution function to construct a new index for feature screening.

Usage

MVSIS(X, Y, nsis)

Arguments

X	The design matrix of dimensions n * p. Each row is an observation vector.
Y	The response vector of dimension n * 1.
nsis	Number of predictors recruited by MVSIS. The default is n/log(n).

Value

the labels of first nsis largest active set of all predictors

Author(s)

Xuewei Cheng [e-mail]

References

Cui, H., Li, R., & Zhong, W. (2015). Model-free feature screening for ultrahigh dimensional discriminant analysis. Journal of the American Statistical Association, 110(510), 630-641.

Examples

n <- 100
p <- 200
rho <- 0.5
data <- GendataLGM(n, p, rho)
data <- cbind(data[[1]], data[[2]])
colnames(data)[1:ncol(data)] <- c(paste0("X", 1:(ncol(data) - 1)), "Y")
data <- as.matrix(data)
X <- data[, 1:(ncol(data) - 1)]
Y <- data[, ncol(data)]
A <- MVSIS(X, Y, n / log(n))
A

MFSIS documentation built on June 22, 2024, 9:42 a.m.