On sample allocation for effective EBLUP estimation of small area totals - "Experimental Allocation"
The demand of regional or small area statistics produced from large-scale surveys such as Finnish unemployment survey has raised needs for developing the tools of optimal sample allocation on area level. However, most commonly used allocation methods aim at producing efficient direct areal estimates. What typically happens is that several areas receive little or none observations, and therefore one has to resort to indirect estimation methods. Best-known of these methods and perhaps most widely used are nested-error regression type model-based estimators. For this reason should areal sample allocation be implemented in such a way that it would lead to efficient estimation in the case of an indirect estimator. In this research an attempt was made to solve this problem by developing an experimental allocation method through simulations. The functioning of this new method has been tested by comparing it to equal and proportional allocation. Different allocation criteria such as values of average absolute relative bias and efficiency are examined through simulation studies with Finnish unemployment data.(author's abstract)
- Brackstone G.J. (2002): Strategies and Approaches for Small Area Statistics. "Survey Methodology", No. 28.
- Falorsi P.D., Righi P. (2008): A Balanced Sampling Approach for Multiway Stratification for Small Area Estimation. "Survey Methodology", No. 34.
- Lehtonen R., Sarndal C.E., Veijanen A. (2003): The Effect of Model Choice in Estimation for Domains, Including Small Domains. "Survey Methodology", No. 29.
- Longford N.T. (2006): Sample Size Calculation for Small-Area Estimation. "Survey Methodology", No. 32.
- Nissinen K. (2009): Small Area Estimation With Linear Mixed Models From Unit-Level Panel and Rotating Panel Data. University of Jyväskylä Departement of Mathematics and Statistics, Report 117.
- Rao J.N.K. (2003): Small Area Estimation. John Wiley & Sons, New York.