RMRCE: RMRCE

In zji90/RMRCE: RMRCE: Regularized Maximum Rank Correlation Estimator

Description

Regularized Maximum Rank Correlation Estimator

Usage

RMRCE(X, Y, lambda, alpha = 5)

Arguments

X	A numeric matrix of explanatory variables.
Y	A numeric vector of response.
lambda	Tuning parameter lambda that can be tuned using cross validation. See RMRCE_cv.
alpha	Tuning parameter alpha that can be tuned using cross validation. See RMRCE_cv. Default value is 5.

Details

This function fits RMRCE (Regularized Maximum Rank Correlation Estimator). It is recommended that the tuning parameters be tuned using cross validation (see RMRCE_cv). RMRCE may need some time to finish with large datasets.

Value

A numeric vector of regression coefficients.

Author(s)

Fang Han, Hongkai Ji, Zhicheng Ji, Honglang Wang <[e-mail]>

Examples

Y <- rnorm(100)
X <- cbind(Y+rnorm(100,sd=0.1),-0.5*Y+rnorm(100,sd=0.1),rnorm(100,sd=0.1))
fit <- RMRCE(X,Y,0.01,5)

zji90/RMRCE documentation built on May 31, 2019, 8:32 a.m.