Electronic Journal of Statistics

A noninformative Bayesian approach for selecting a good post-stratification

Patrick Zimmerman and Glen Meeden

Full-text: Open access


In the standard design approach to survey sampling prior information is often used to stratify the population of interest. A good choice of the strata can yield significant improvement in the resulting estimator. However, if there are several possible ways to stratify the population, it might not be clear which is best. Here we assume that before the sample is taken a limited number of possible stratifications have been defined. We will propose an objective Bayesian approach that allows one to consider these several different possible stratifications simultaneously. Given the sample the posterior distribution will assign more weight to the good stratifications and less to the others. Empirical results suggest that the resulting estimator will typically be almost as good as the estimator based on the best stratification and better than the estimator which does not use stratification. It will also have a sensible estimate of precision.

Article information

Electron. J. Statist., Volume 12, Number 2 (2018), 2515-2536.

Received: March 2018
First available in Project Euclid: 27 July 2018

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62D05: Sampling theory, sample surveys
Secondary: 62F15: Bayesian inference

Finite population sampling stratification prior information stepwise Bayes

Creative Commons Attribution 4.0 International License.


Zimmerman, Patrick; Meeden, Glen. A noninformative Bayesian approach for selecting a good post-stratification. Electron. J. Statist. 12 (2018), no. 2, 2515--2536. doi:10.1214/18-EJS1461. https://projecteuclid.org/euclid.ejs/1532678418

Export citation


  • Cochran, W. (1977)., Sampling Techniques (Third ed.). Wiley.
  • Elliott, M. R. and Little, R. J. A. (2000). Model-based alternatives to trimming survey weights., Jouirnal of Official Statistics, 16:191–209.
  • Fuller, W. (2009)., Sampling Statistics. Wiley.
  • Ghosh, M. and Meeden, G. (1997)., Bayesian Methods for Finite Population Sampling. Chapman and Hall.
  • Golder, P. and Yeomans, K. (1973). The use of cluster analysis for stratification., Journal of the Royal Statistical Society, Series C, 22:213–219.
  • Hartley, H. O. and Rao, J. N. K. (1968). A new estimation theory for sample surveys., Biometrika, 55:159–167.
  • Hsuan, F. (1979). A stepwise bayes procedure., Annals of Statistics, 7:860–868.
  • Johnson, B. (1971). On admissible estimators for certain fixed sample binomial problems., Annals of Mathematical Statistics, 42:1579–1587.
  • Little, R. J. A. (1993). Post-stratification: A modeler’s perspective., Journal of the American Statistical Association, 88:1001–1012.
  • Lumley, T. (2010)., Comples Surveys, A Guide to Analysis Using R. Wiley.
  • Pla, L. (1991). Determining stratum boundaries with multivariate real data., Biometrics, 47:1409–1422.
  • R Core Team (2017)., R: A language and evironment for statistical computing. R Foundation for Statistical Computing. http://R-project.org.
  • Rubin, D. B. (1981). The bayesian bootstrap., Annals of Statistics, 9:130–134.
  • Rudin, W. (1976)., Principles of Mathematical Analysis. McGraw-Hill, 3rd edition.
  • Si, Y., Pilla, N., and Gelman, A. (2015). Bayesian nonparametric weighted sampling inference., Bayesian Analysis, 10:605–625.
  • Zimmerman, P. (2013)., Survey Sampling and Multiple Stratifications. PhD thesis, University of Minnesota.