residual_est: Residual estimation of calibration

In vardpoor: Variance Estimation for Sample Surveys by the Ultimate Cluster Method

Description

Computes the estimation residuals of calibration.

Usage

residual_est(Y, X, weight, q, dataset = NULL, checking = TRUE)

Arguments

Y	Matrix of the variable of interest.
X	Matrix of the auxiliary variables for the calibration estimator. This is the matrix of the sample calibration variables.
weight	Weight variable. One dimensional object convertible to one-column data.frame.
q	Variable of the positive values accounting for heteroscedasticity. One dimensional object convertible to one-column data.frame.
dataset	Optional survey data object convertible to data.table.
checking	Optional variable if this variable is TRUE, then function checks data preparation errors, otherwise not checked. This variable by default is TRUE.

Details

The function implements the following estimator:

e_k=Y_k-X_k^{'}B

where

\hat{B} = ≤ft(∑_{s} weight_k q_k X_k X^{'}_{k} \right)^{-1} ≤ft(∑_{s} weight_k q_k X_k Y_k \right)

.

Value

A list with objects are returned by the function:

• residuals - a numeric data.table containing the estimated residuals of calibration.

• betas - a numeric data.table containing the estimated coefficients of calibration.

References

Sixten Lundstrom and Carl-Erik Sarndal. Estimation in the presence of Nonresponse and Frame Imperfections. Statistics Sweden, 2001, p. 43-44.

See Also

domain, lin.ratio, linarpr, linarpt, lingini, lingini2, lingpg, linpoormed, linqsr, linrmpg, vardom, vardomh, varpoord, variance_est, variance_othstr

Examples

Y <- matrix(rchisq(10, 3), 10, 1)
X <- matrix(rchisq(20, 3), 10, 2)
w <- rep(2, 10)
q <- rep(1, 10)
residual_est(Y, X, w, q)

### Test2
Y <- matrix(rchisq(10, 3), 10, 1)
X <- matrix(c(rchisq(10, 2), rchisq(10, 2) + 10), 10, 2)
w <- rep(2, 10)
q <- rep(1, 10)
residual_est(Y, X, w, q)
as.matrix(lm(Y ~ X - 1, weights = w * q)$residuals)

vardpoor documentation built on Nov. 30, 2020, 5:08 p.m.