MCEM: MCEM Algorithm for Missing Response Variables

In DLMRMV: Distributed Linear Regression Models with Response Missing Variables

MCEM Algorithm for Missing Response Variables

Description

Implements the Monte Carlo EM algorithm for handling missing response data in linear regression models.

Usage

MCEM(data, d = 5, tol = 0.01, nb = 50)

Arguments

data	A data frame with the response variable in the first column and predictors in the remaining columns.
d	Initial convergence threshold. Defaults to 5.
tol	Termination tolerance. Defaults to 0.01.
nb	Maximum number of iterations. Defaults to 50.

Details

This function implements the Monte Carlo Expectation-Maximization (MCEM) algorithm to handle missing response variables in linear regression models. The algorithm iteratively imputes missing responses and updates regression coefficients until convergence.

Value

A list containing the following components:

Yhat	Imputed response vector with missing values filled in.
betahat	Final regression coefficients.
iterations	Number of iterations performed.

Examples

  # Create dataset with 20% missing responses
  set.seed(123)
  data <- data.frame(
    Y = c(rnorm(80), rep(NA, 20)),
    X1 = rnorm(100),
    X2 = runif(100)
  )
  result <- MCEM(data, d = 5, tol = 0.001, nb = 100)
  print(result$Yhat)  # Imputed response vector
  print(result$betahat)  # Final regression coefficients
  print(result$iterations)  # Number of iterations performed

DLMRMV documentation built on Aug. 8, 2025, 6:27 p.m.