eblupfh_ns {saens} | R Documentation |
Synthetic Estimator.
Description
Synthetic estimator is one of the simple methods to obtain predicted values of mean specific area parameters, which the direct estimates are unknown. Based on estimated of parameter coefficient models using Empirical Best Unbiased Prediction (EBLUP), the synthetic estimator is obtained by calibrating the estimated parameter coefficient to the auxiliary variables.
Usage
eblupfh_ns(
formula,
data,
vardir,
method = "REML",
maxiter = 100,
precision = 1e-04,
scale = FALSE,
print_result = TRUE
)
Arguments
formula |
an object of class formula that contains a description of the model to be fitted. The variables included in the formula must be contained in the data. |
data |
a data frame or a data frame extension (e.g. a tibble). |
vardir |
vector or column names from data that contain variance sampling from the direct estimator for each area. |
method |
Fitting method can be chosen between 'ML' and 'REML' |
maxiter |
maximum number of iterations allowed in the Fisher-scoring algorithm. Default is 100 iterations. |
precision |
convergence tolerance limit for the Fisher-scoring algorithm. Default value is 0.0001. |
scale |
scaling auxiliary variable or not, default value is FALSE. |
print_result |
print coefficient or not, default value is TRUE. |
Details
The model is defined as response ~ auxiliary variables, where the response variable, of numeric type, may contain NA values. When the response variable contains NA, it will be estimated using a synthetic estimator.
Value
The function returns a list with the following objects df_res
and fit
:
df_res
a data frame that contains the following columns:
-
y
variable response
-
eblup
estimated results for each area
-
random_effect
random effect for each area
-
vardir
variance sampling from the direct estimator for each area
-
mse
Mean Square Error
-
cluster
cluster information for each area
-
rse
Relative Standart Error (%)
fit
a list containing the following objects:
-
estcoef
a data frame with the estimated model coefficients in the first column (beta), their asymptotic standard errors in the second column (std.error), the t-statistics in the third column (tvalue) and the p-values of the significance of each coefficient in last column (pvalue)
-
model_formula
model formula applied
-
method
type of fitting method applied (ML
orREML
)
-
random_effect_var
estimated random effect variance
-
convergence
logical value that indicates the Fisher-scoring algorithm has converged or not
-
n_iter
number of iterations performed by the Fisher-scoring algorithm.
-
goodness
vector containing several goodness-of-fit measures: loglikehood, AIC, and BIC
References
Rao, J. N., & Molina, I. (2015). Small area estimation. John Wiley & Sons.
Examples
library(saens)
m1 <- eblupfh_ns(y ~ x1 + x2 + x3, data = mys, vardir = "var")
m1 <- eblupfh_ns(y ~ x1 + x2 + x3, data = mys, vardir = ~var)