| mspeFHsumca | R Documentation |
This function returns MSPE estimator with the combination of linearization and resampling appoximation method called "Sumca", for Fay Herriot model.
mspeFHsumca(Y, X, D, K = 50, method = 1)
Y |
(vector). It represents the response value for Fay Herriot model. |
X |
(matrix). Stands for the available auxiliary values. |
D |
(vector). It represents the knowing sampling variance for Fay Herriot model. |
K |
(integer). It represents the Monte-Carlo sample size for "Sumca". Default value is 50. |
method |
It represents the variance component estimation method. See "Details". |
This method was proposed by J. Jiang, P. Lahiri, and T. Nguyen, sumca method combines the advantages of linearization and resampling methods and obtains unified, positive, low-computation burden and second-order unbiased MSPE estimators.
Default value for method is 1, method = 1 represents the MOM method , method = 2 and method = 3 represents ML and REML method, respectively.
This function returns a list with components:
MSPE |
(vector) MSPE estimates for Fay Herriot model. |
bhat |
(vector) Estimates of the unknown regression coefficients. |
Ahat |
(numeric) Estimates of the variance component. |
Peiwen Xiao, Xiaohui Liu, Yuzi Liu, Jiming Jiang, and Shaochu Liu
J. Jiang and M. Torabi. Sumca: simple; unified; monte carlo assisted approach to second order unbiased mean squared prediction error estimation. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 82(2):467-485, 2020.
X = matrix(runif(10 * 3), 10, 3) X[,1] = rep(1, 10) D = (1:10) / 10 + 0.5 Y = X %*% c(0.5,1,1.5) + rnorm(10, 0, sqrt(2)) + rnorm(10, 0, sqrt(D)) mspeFHsumca(Y, X, D, K = 50, method = 1)