On the Simulation Study of Jackknife and Bootstrap MSE Estimators of a Domain Mean Predictor for Fay‑Herriot Model

Acta Universitatis Lodziensis. Folia Oeconomica

Małgorzata Karolina Krzciuk¹ 

[1] University of Economics in Katowice. Department of Statistics, Econometrics and Mathematics;

关键词: estimators of MSE;    jackknife;    parametric bootstrap;    Empirical Best Linear Unbiased Predictor;    Fay‑Herriot model;    simulation;   

DOI  :  10.18778/0208-6018.331.11

来源: DOAJ

【 摘 要 】

We consider the problem of the estimation of the mean squared error (MSE) of some domain mean predictor for Fay‑Herriot model. In the simulation study we analyze properties of eight MSE estimators including estimators based on the jackknife method (Jiang, Lahiri, Wan, 2002; Chen, Lahiri, 2002; 2003) and parametric bootstrap (Gonzalez‑Manteiga et al., 2008; Buthar, Lahiri, 2003). In the standard Fay‑Herriot model the independence of random effects is assumed, and the biases of the MSE estimators are small for large number of domains. The aim of the paper is the comparison of the properties of MSE estimators for different number of domains and the misspecification of the model due to the correlation of random effects in the simulation study.

【 授权许可】

Unknown