IROmiss (version 1.0.2)

SimRegDat: Simulate Incomplete Data for High-Dimensional Linear Regression.

Description

Simulate incomplete data for high-dimensional linear regression with dependent or independent covariatesRegICRO(x,y...).

Usage

SimRegDat(n = 100, p = 200, coef, data.type = "indep",
miss.type="MCAR", rate = 0.1)

Arguments

n

Number of observations, default of 100.

p

Number of covariates, default of 200.

coef

A px1 vector of coefficients for the linear regression model. The intercept coefficient is default to 1.

data.type

When data.type=="indep", it simulates the data with independent covariates, each covariate independently follow the normal distribution with mean 0 and variance 4. When data.type=="dep", it simulates the data with dependent covariates with "band" dependent structure, see SimGraDat for detail. The default data type is "indep".

miss.type

miss.type=="MCAR" refer to the case of missing completely at random. when miss.type=="MAR", the missing probability for each data point is proportional to the mean of its conditional normal distribution, the default missing type is "MCAR".

rate

Missing rate, the default value is 0.1.

Value

x

nxp covariates matrix.

y

nx1 responses.

coef

px1 vector of coefficients for the linear regression model.

%% ...

References

Liang, F., Song, Q. and Qiu, P. (2015). An Equivalent Measure of Partial Correlation Coefficients for High Dimensional Gaussian Graphical Models. J. Amer. Statist. Assoc., 110, 1248-1265.

Liang, F. and Zhang, J. (2008) Estimating FDR under general dependence using stochastic approximation. Biometrika, 95(4), 961-977.

Liang, F., Jia, B., Xue, J., Li, Q., and Luo, Y. (2018). An Imputation Regularized Optimization Algorithm for High-Dimensional Missing Data Problems and Beyond. Submitted to Journal of the Royal Statistical Society Series B.

Examples

# NOT RUN {
library(IROmiss)
p <- 200
beta <- rep(0,p)
beta[1:5] <- c(1, 2, -1.5, -2.5, 5)
SimRegDat(n = 100, p = 200, coef = beta, data.type = "dep", 
miss.type="MAR", rate = 0.1)
         
# }