gencalibRaking: Generalized calibration using raking ratio

In RJauslin/StratifiedSampling: Different Methods for Stratified Sampling

Generalized calibration using raking ratio

Description

This function is inspired by the function calib of the package sampling. It computes the g-weights of the calibration estimator.

Usage

gencalibRaking(Xs, Zs, d, total, q, max_iter = 500L, tol = 1e-09)

Arguments

Xs	A matrix of calibration variables.
Zs	A matrix of instrumental variables with same dimension as Xs.
d	A vector, the initial weights.
total	A vector that represents the initial weights.
q	A vector of positive value that account for heteroscedasticity.
max_iter	An integer, the maximum number of iterations. Default = 500.
tol	A scalar that represents the tolerance value for the algorithm. Default = 1e-9.

Details

More details on the different calibration methods can be read in Tillé Y. (2020).

Value

A vector, the value of the g-weights.

References

Tillé, Y. (2020). Sampling and estimation from finite populations. Wiley, New York

RJauslin/StratifiedSampling documentation built on Feb. 5, 2025, 4:18 a.m.