data_binlogitnorm {hbsaems} | R Documentation |
Simulated Binomial–Logit-Normal data (area-level)
Description
The data_binlogitnorm
dataset contains simulated data for 50 areas based on a
Binomial–Logit-Normal model. It includes area-level covariates, true
probability parameters, sample sizes, observed counts, direct estimators,
sampling variances, and true latent values.
Usage
data_binlogitnorm
Format
A data frame with 50 rows and 13 variables:
- n
Sample size per area
- y
Observed success count per area
- p
Direct estimator of proportion
- x1, x2, x3
Auxiliary area-level covariates
- u_true
True area-level random effect
- eta_true
True linear predictor (logit scale)
- p_true
True probability per area
- psi_i
Sampling variance of logit-transformed direct estimator
- y_obs
Simulated noisy version of eta (logit scale)
- p_obs
Estimated proportion via inverse logit of y_obs
- group
Area ID (1–100) for random effects formula specifying the grouping structure in the data.
- sre
An optional grouping factor mapping observations to spatial locations.
Details
This dataset is intended for evaluating small area estimation models under Binomial–Logit-Normal assumptions.
Source
Simulated data based on a Binomial–Logit-Normal model