Bootstrap for Estimating the MSE of the Spatial EBLUP Articles uri icon

authors

  • MOLINA PERALTA, ISABEL
  • Salvati, Nicola
  • Pratesi, Monica

publication date

  • August 2009

start page

  • 441

end page

  • 458

issue

  • 3

volume

  • 24

International Standard Serial Number (ISSN)

  • 0943-4062

Electronic International Standard Serial Number (EISSN)

  • 1613-9658

abstract

  • This work assumes that the small area quantities of interest follow a Fay&-Herriot model with spatially correlated random area effects. Under this model, parametric and nonparametric bootstrap procedures are proposed for estimating themean squared error of the empirical best linear unbiased predictor (EBLUP). A simulation study based on the Italian Agriculture Census 2000 compares bootstrap and analytical estimates of the MSE and studies their robustness to non-normality. Results indicate lower bias for the non-parametric bootstrap under specific departures from normality.