var_pi: Variance estimator free of joint inclusion probability...

In ksauby/ACS: Adaptive Cluster Sampling

Variance estimator free of joint inclusion probability calculations for unequal probability sampling

Description

This gives equation 9 on page 10 in Berger and Tille 2009.

Usage

var_pi(n, y, pi_i_values, estimator)

Arguments

n	sample size (an integer value).
y	need description
pi_i_values	vector of inclusion probabilities, if not calculated using this function. Default is NULL.
estimator	Options include "Hajek".

References

\insertRef

hajek1964asymptoticACSampling \insertRefberger2009samplingACSampling

Examples

# Hajek Approximation
library(dplyr)
library(magrittr)
Z = createACS(Thompson1990Fig1Pop, seed=3, n1=30, "y_value", criterion=0)
Z_summary <- Z %>% 
	dplyr::filter(Sampling!="Edge") %>%
	group_by(NetworkID) %>%
	filter(NetworkID > 0) %>%
	dplyr::summarise(
		m = m[1],
		y_total = sum(y_value, na.rm=TRUE)
	)
var_y_HT(
	N = dim(Thompson1990Fig1Pop)[1], 
	n1 = dim(Thompson1990Figure1Sample)[1], 
	m = Z_summary$m, 
	y = Z_summary$y_total
)
pi_i_values <- pi_i(N=900,n1=30, m=Z_summary$m)
Hajek_b(pi_i=pi_i_values, n=30)
var_pi(
	n = 30, 
	y = Z_summary$y_total, 
	pi_i_values = pi_i_values,
	estimator = "Hajek"
)

ksauby/ACS documentation built on Aug. 18, 2022, 3:33 a.m.