Estimating and Mapping Disaggregated Indicators

Functions that support estimating, assessing and mapping regional disaggregated indicators. So far, estimation methods comprise direct estimation, the model-based unit-level approach Empirical Best Prediction (see "Small area estimation of poverty indicators" by Molina and Rao (2010) ), the area-level model (see "Estimates of income for small places: An application of James-Stein procedures to Census Data" by Fay and Herriot (1979) ) and various extensions of it (adjusted variance estimation methods, log and arcsin transformation, spatial, robust and measurement error models), as well as their precision estimates. The assessment of the used model is supported by a summary and diagnostic plots. For a suitable presentation of estimates, map plots can be easily created. Furthermore, results can easily be exported to excel. For a detailed description of the package and the methods used see "The R Package emdi for Estimating and Mapping Regionally Disaggregated Indicators" by Kreutzmann et al. (2019) and the second package vignette "A Framework for Producing Small Area Estimates Based on Area-Level Models in {R}".


emdi 1.1.5

  • Tests updated to deal with new random number generation in R
  • Some spelling improved

emdi 1.1.4

  • Fixed Bug in summary: R2 calculation with MuMIn is now fully working
  • Added feature: formula used in fixed is now preserved, even if passed to ebp as a variable

emdi 1.1.3

  • The function compare_plot now benefits from a legend in all plots.
  • Changes to be compatible with the forthcoming version of the MuMIn package.

emdi 1.1.2

  • The function compare_plot has been added to allow for an easy comparison between direct and model based estimates.
  • Argument checks have been added, and improved
  • Additional example in map_plot in order to explain the mapping table
  • The datasets have been improved to allow for more realistic examples
  • Small bug fixes
  • Updated Vignette

emdi 1.1.1

  • The function ebp benefits from a new parameter called seed that allows reproducibility even when the function is run in parallel mode.
  • Argument checks have been added, and improved
  • Additional example in map_plot and direct
  • Updated Vignette

emdi 1.1.0

  • A new function direct is made available, which provides direct estimation for small areas.
  • The function ebp now allows for a user-defined threshold.
  • The function ebp is now able to perform a semi-parametric wild bootstrap for MSE estimation.
  • The function ebp has new default value for parallelization that automatically adopts for the operating system.
  • The two data sets eusilcA_smp and eusilcA_pop have been updated.
  • For the function map_plot additional customization is now applicable.
  • All methods for emdi model except plot are extended for emdi direct.
  • subset and have been added as methods for class emdi.estimators

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


2.1.0 by Soeren Pannier, 3 months ago

Browse source code at

Authors: Sylvia Harmening [aut] , Ann-Kristin Kreutzmann [aut] , Soeren Pannier [aut, cre] , Felix Skarke [aut] , Natalia Rojas-Perilla [aut] , Nicola Salvati [aut] , Timo Schmid [aut] , Matthias Templ [aut] , Nikos Tzavidis [aut] , Nora Würz [aut]

Documentation:   PDF Manual  

Task views:

GPL-2 license

Imports nlme, moments, ggplot2, MuMIn, gridExtra, openxlsx, reshape2, stats, stringr, parallelMap, HLMdiag, parallel, boot, MASS, readODS,, saeRobust, spdep

Suggests testthat, R.rsp, simFrame, laeken, rgeos, maptools, graphics

See at CRAN