DIRMR (version 0.5.0)

MOPXEM: MOPXEM

Description

The MOPXEM method is an improved EM algorithm that combines the monotonic super-relaxation strategy with the PXEM strategy. The main idea of the MOPXEM method is to accelerate the EM algorithm using the ULS strategy, while simultaneously expanding and optimizing the model parameters using the PX-EM strategy.

Usage

MOPXEM(data,df1,omega,maxiter)

Value

Y01

The response variable value after projection

Yhat

The estimated response variable value after projection

Arguments

data

The real data sets with missing data used in the method

df1

The real data sets used in the method

omega

A variable of this method

maxiter

The maximum number of iterations

Author

Guangbao Guo,Yu Li

Examples

set.seed(99)
library(MASS)
library(mvtnorm)
n=50;p=6;q=5;M=2;omega=0.15;ratio=0.1;maxiter=15;nob=round(n-(n*ratio))
dd.start=1;sigma2_e.start=1
X0=matrix(runif(n*p,0,2),ncol=p)
beta=matrix(rnorm(p*1,0,3),nrow=p)
Z0=matrix(runif(n*q,2,3),ncol=q)
e=matrix(rnorm(n*1,0,sigma2_e.start),n,1)
b=matrix(rnorm(q*1,0,1),q,1)
Y0=X0
df1=data.frame(Y=Y0,X=X0,Z=Z0)
misra=function(data,ratio){
  nob=round(n-(n*ratio))
  data[sample(n,n-nob),1]=NA
  return(data)}
data=misra(data=df1,ratio=0.1)
MOPXEM(data,df1,omega=0.15,maxiter=15)