MNR: Markov Neighborhood Regression for High-Dimensional...

In equSA: Learning High-Dimensional Graphical Models

Description

Construct confidence intervals and assess p-values in high-dimensional linear and generalized linear models.

Usage

MNR(x,y,family='gaussian',penalty='lasso',tune='bic',alpha1=0.1,alpha2=0.05,level=0.95)

Arguments

x	The design matrix, of dimensions nxp, without an intercept. Each row is an observation vector.
y	The response vector of dimension nx1. Quantitative for family='gaussian', binary (0-1) for family='binomial'. For family='cox', y should be an object of class Surv, as provided by the function Surv() in the package survival.
family	Response type (see above).
penalty	The penalty to be applied in the regularized likelihood subproblems. 'lasso' (the default), 'MCP', or 'SCAD' are provided. See package SIS for detail.
tune	Method for tuning the regularization parameter of the penalized likelihood subproblems and of the final model selected by (I)SIS. Options include tune='bic', tune='ebic', tune='aic', and tune='cv'.
alpha1	The significance level of correlation screening in the ψ-learning algorithm, see R package equSA for detail. In general, a high significance level of correlation screening will lead to a slightly large separator set, which reduces the risk of missing important variables in the conditioning set. In general, including a few false variables in the conditioning set will not hurt much the accuracy of the ψ-partial correlation coefficient, the default value is 0.1.
alpha2	The significance level of ψ-partial correlation coefficient screening for estimating the adjacency matrix, see equSA, the default value is 0.05.
level	the confidence level required, the default value is 0.95

Value

CI	Estimated confidence intervals for all coefficients.
coef	px1 estimated regression coefficients for all variables.
pvalue	px1 estimated p-values for all variables.

Author(s)

Bochao [e-mail] and Faming Liang

References

Liang, F., Xue, J. and Jia, B. (2018). Markov Neighborhood Regression for High-Dimensional Inference. Submitted to J. Amer. Statist. Assoc.

Examples

 
library(equSA)
p <- 500
coef_true <- rep(0,p)
coef_true[1:5] <- c(2,4,-3,-5,10)
coef <- c(1,coef_true)
data <- SimMNR(n = 200, p = 500, coef = coef, family = "gaussian")
MNR(data$x, data$y, family = "gaussian")

equSA documentation built on May 6, 2019, 1:06 a.m.