Package index • fastsae

Classical Area-Level Models (EBLUP)

High-performance C++ implementation of Fay-Herriot models

eblup_fh(): Empirical Best Linear Unbiased Prediction based on a Fay-Herriot Model.
eblup_sfh(): Empirical Best Linear Unbiased Prediction based on a Spatial Fay-Herriot Model.
eblup_stfh(): Empirical Best Linear Unbiased Prediction based on a Spatio-Temporal Fay-Herriot Model.

Hierarchical Bayesian SAE using Integrated Nested Laplace Approximations (INLA) across 6 distributions with spatial and spatio-temporal effects

Engine objects for the Hierarchical Bayes models: INLA (default) or MCMC with NumPyro / JAX (optional Python backend)

inla_engine() jax_engine() print(<fastsae_engine>): Estimation engines for the Hierarchical Bayes models
setup_numpyro_env(): Set up, or check, the Python environment for the NumPyro / JAX engine

Nested area-subarea level models (Torabi & Rao, 2014) with both area and subarea random effects via REML EBLUP and Bayesian INLA

eblup_twofold(): Empirical Best Linear Unbiased Prediction under a Two-fold Fay-Herriot Model.
hb_twofold(): Two-Fold Hierarchical Bayes for Sub-Area Level Small Area Estimation
hb_ratio(): Hierarchical Bayes Ratio Model for a Sub-Proportion of a Parent Indicator

Battese-Harter-Fuller models for unit-level survey data via REML EBLUP and Bayesian INLA

eblup_bhf(): Empirical Best Linear Unbiased Prediction (EBLUP) for the Battese-Harter-Fuller Model
hb_unit(): Hierarchical Bayes for Unit-Level Small Area Estimation

Spatial weights, spatial autocorrelation tests, and smoothing of sampling variances

create_weights(): Create Spatial Proximity and Weights Matrix
spatial_test(): Pre-Modeling Spatial Diagnostic and Autocorrelation Tests
gvf_smooth(): Generalized Variance Function (GVF) Smoothing for Sampling Variances
effective_trials(): Effective Sample Sizes of Direct Proportions

Universal diagnostic framework and ggplot2 visualization methods

diagnose(): Diagnostic Evaluation of Small Area Estimation Models
autoplot(<fastsae_diagnose>): Autoplot Method for fastsae_diagnose Objects
autoplot(<fastsae>) autoplot(<list>): Autoplot Method for fastsae Objects
summary(<fastsae>): Summarize a fastsae object
coef(<fastsae>): Extract coefficients from a fastsae object
fitted(<fastsae>): Extract fitted values (EBLUP or HB) from a fastsae object
residuals(<fastsae>): Extract residuals from a fastsae object
print(<fastsae>): Print a fastsae object
print(<summary.fastsae>): Print summary of a fastsae object

Calibrate small area estimates to aggregate targets via Ratio, Difference, Optimal, and Logit methods (Rao & Molina, 2015)

benchmark_sae() print(<fastsae_benchmark>) summary(<fastsae_benchmark>) autoplot(<fastsae_benchmark>) plot(<fastsae_benchmark>): Benchmark Small Area Estimation Predictions to Aggregate Targets

Unified spatial choropleth mapping (‘satu pintu’), model concordance evaluation, and official publication exports

map_sae(): Unified Spatial Choropleth Mapping for Small Area Estimates
compare_sae() print(<fastsae_comparison>) summary(<fastsae_comparison>) plot(<fastsae_comparison>) autoplot(<fastsae_comparison>): Compare Two Small Area Estimation Models
step_sae(): Stepwise Selection of the Covariates of a Small Area Model
export_sae(): Export Small Area Estimation Results to Excel or CSV
add_reliability_flags(): Add Official Statistical Reliability Flags
plot(<fastsae>): Plot method for fastsae objects

Utilities to simulate area-level cross-sectional, panel, and spatial weight matrices

sim_area_data(): Simulate Multi-Distribution Small Area Data with Spatial Autocorrelation
sim_series_data(): Simulate Spatio-Temporal Multi-Distribution Small Area Data

Built-in empirical and synthetic survey datasets

mys: mys: mean years of schooling of people with disabilities
mys_panel: mys_panel: mean years of schooling of people with disabilities, 2016-2026
mys_proxmat: Example proximity matrix
cornsoybean: Corn and Soybean Survey and Satellite Data in 12 Iowa Counties
cornsoybeanmeans: Corn and Soybean Mean Number of Pixels per Segment for 12 Iowa Counties
sim_area: Multi-Distribution Synthetic Area-Level Dataset
sim_panel: Multi-Distribution Spatio-Temporal Panel Dataset