Comparison of Small Area Estimations by Sample Sizes

  • Kim, Jung-O (Department of Statistics, Hankuk University of Foreign Studies) ;
  • Shin, Key-Il (Department of Statistics, Hankuk University of Foreign Studies)
  • Published : 2006.12.31


Model-based methods are generally used for small area estimation. Recently Shin and Lee (2003) suggested a method which used spatial correlations between areas for data set including some auxiliary variables. However in case of absence of auxiliary variables, Direct estimator is used. Even though direct estimator is unbiased, the large variance of the estimator restricts the use for small area estimation. In this paper, we suggest new estimators which take into account spatial correlation when auxiliary variables are not available. We compared Direct estimator and the newly suggested estimators using MSE, MAE and MB.


  1. 김재두, 신기일, 이상은 (2005). 공간 시계열 모형을 이용한 소지역 추정, 응용통계연구, 18권, 627-637
  2. 신기일, 이상은 (2003). Model-Data Based Small Area Estimation. The Korean Communications in Statistics, Vol. 10, 637-645
  3. 이계오 (2002). 소지역 추정법에 관한 시군구 실업 통계 개발, 통계청 최종 보고서
  4. Cressie, N. (1993). Statistics for Spatial Data, John Wiley and Sons, Inc., New York
  5. Freeman, M.F. and Tukey, J.W. (1950). Transformation Related to the Angular and the Square Root. Annals of Mathematical Statistics, 607-611
  6. Falorsi, P.D. Falorsi, S. and Dusso A. (1994). Empirical Comparison of Small Area Estimation Methods for the Italian Labour Force Survey. Survey Methodology, Vol. 20, 171-175
  7. Ghosh, M. Maiti, T. and Roy, A. (2006). Influence Functions and Robust Bayes and Empirical Bayes Small Area Estimation. Malay Ghosh 초청세미나. 조사통계연구회
  8. Rao, J.N.K. (2003). Small Area Estimation, John Wiley and Sons, Inc, New York
  9. Schaible, W.L. (1978). Choosing Weights for Composite Estimators for Small Area Statistics, Proceedings of the Section on Survey Research Methods. American Statistical Association, 741-746