Skip to contents

Design-based vs model-based variance identities (chapter 26)

Source: R/brus_native.R
morie_survey_variances.Rd

Equations 26.2 to 26.5 of Brus (2022), plus the small-area, repeated survey, response surface and validation pieces of chapters 14 to 25: small-area mean (14.15), trend weights (15.4), GLS estimator (15.10), linear working model (16.1), OLS beta and prediction variance (20.2, 20.3), classification indicator (25.8).

Usage

morie_survey_variances(
  sigma2 = NA,
  n = NA,
  rho_bar = NA,
  s2 = NA,
  n_population = NA,
  xbar_d = NULL,
  beta_hat = NULL,
  v_d = NA,
  times = NULL,
  x = NULL,
  c_mat = NULL,
  zhat = NULL,
  beta0 = NA,
  beta1 = NA,
  x_val = NA,
  x_design = NULL,
  z_obs = NULL,
  sigma2_eps = NA,
  x0 = NULL,
  c_hat = NULL,
  c_true = NULL,
  u = NULL
)

Arguments

sigma2, n, rho_bar, s2, n_population

Chapter 26 pieces.

xbar_d, beta_hat, v_d

Small-area pieces.

times

Trend.

x, c_mat, zhat

GLS pieces.

beta0, beta1, x_val

Model 16.1.

x_design, z_obs

OLS pieces.

sigma2_eps, x0

Prediction var.

c_hat, c_true, u

Classification pieces.

Value

List of the requested quantities.

Examples

morie_survey_variances()
#> list()