, Volume 68, Issue 1, pp 95–103 | Cite as

On stochastic optimization in sample allocation among strata

  • Marcin Kozak
  • Hai Ying Wang


The usefulness of stochastic optimization for sample allocation in stratified sampling is studied. Three models of stochastic optimization are compared: E-Model, Modified E-model and V-model, recently presented by Díaz-García and Garay-Tápia (Comput. Statistics Data Anal., 3016–3026, 51, 2007), with the classical sample allocation, which distributes the costs among strata in such a way that the variance of an estimator is minimized. To make the comparison, a simulation study was conducted. None of the methods was the most efficient for all cases, but usually the classical allocation was the most efficient, followed by the E-model, quite similar to the former.

Key Words

Stratified sampling Optimization Cost allocation Optimum allocation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Díaz-García, J. D. ánd Garay-Tápia, M.M. (2007) Optimum allocation in stratified surveys: Stochastic programming, Computational Statistics & Data Analysis, 51, 3016–3026.MathSciNetMATHCrossRefGoogle Scholar
  2. Kozak, M. (2006) Multivariate sample allocation: application of random search method, Statistics in Transition, 7(4), 889–900.MathSciNetMATHGoogle Scholar
  3. Sarndal, C. E., Swensson, B. and Wretman, J. (1992) Model Assisted Survey Sampling, Springer-Verlag.Google Scholar

Copyright information

© Sapienza Università di Roma 2010

Authors and Affiliations

  1. 1.Department of Experimental Design and BioinformaticsFaculty of Agriculture and Biology Warsaw University of Life SciencesWarsawPoland
  2. 2.Academy of Mathematics and Systems SciencesChinese Academy of SciencesChina

Personalised recommendations