DocumentCode :
3074631
Title :
A hybrid algorithm for spatial small area estimation under models with complex contiguity
Author :
Sofronov, Georgy
Author_Institution :
Dept. of Stat., Macquarie Univ., Sydney, NSW, Australia
fYear :
2013
fDate :
16-19 April 2013
Firstpage :
25
Lastpage :
30
Abstract :
Estimation of population characteristics for sub-national geographically defined domains such as regions, states, districts and local government areas can be considered one of the important issues of statistical surveys. A general method in small area estimation (SAE) is the use of linear mixed models with area specific random effects to account for between areas variation beyond that explained by auxiliary variables included in the fixed part of the model. In order to use spatial auxiliary information in SAE, it is reasonable to assume that the area random effects (defined, for example, by a contiguity criterion) are correlated. In this paper, we propose a hybrid algorithm based on the Cross-Entropy method to spatial modelling in SAE using Monte Carlo simulation to find a contiguity matrix that maximizes some measure of spatial association between areas. Estimation of the mean squared error of the resulting small area estimators is discussed. The properties of the estimators are evaluated by applying them to the results of farm surveys that have been conducted by the Australian Bureau of Agricultural and Resource Economics.
Keywords :
Monte Carlo methods; demography; estimation theory; matrix algebra; mean square error methods; Monte Carlo simulation; SAE; area specific random effect; complex contiguity; contiguity matrix; cross-entropy method; hybrid algorithm; linear mixed model; mean squared error estimation; population characteristic estimation; spatial small area estimation; statistical surveys; Biological system modeling; Educational institutions; Maximum likelihood estimation; Sociology; Vectors; Cross-Entropy method; combinatorial optimization; hybrid algorithm; small area estimation; spatial model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Differential Evolution (SDE), 2013 IEEE Symposium on
Conference_Location :
Singapore
Type :
conf
DOI :
10.1109/SDE.2013.6601438
Filename :
6601438
Link To Document :
بازگشت