Advertisement

Statistical Papers

, Volume 60, Issue 1, pp 89–104 | Cite as

Application of the full Bayesian significance test to model selection under informative sampling

  • A. SikovEmail author
  • J. M. Stern
Regular Article
  • 119 Downloads

Abstract

Adopting likelihood based methods of inference in the case of informative sampling often presents a number of difficulties, particularly, if the parametric form of the model that describes the sample selection mechanism is unknown, and thus requires application of some model selection approach. These difficulties generally arise either due to complexity of the model holding in the sample, or due to identifiability problems. As a remedy we propose alternative approach to model selection and estimation in the case of informative sampling. Our approach is based on weighted estimation equations, where the contribution to the estimation equation from each observation is weighted by the inverse probability of being selected. We show how weighted estimation equations can be incorporated in a Bayesian analysis, and how the full Bayesian significance test can be implemented as a model selection tool. We illustrate the efficiency of the proposed methodology by a simulation study.

Keywords

Informative sampling Design variables Inclusion probability Bayesian significance measures Horvitz–Thompson estimator Population distribution Sample distribution 

Notes

Acknowledgments

The authors are grateful for the support of IME-USP, the Institute of Mathematics and Statistics of the University of São Paulo; FAPESP - the State of São Paulo Research Foundation (grant CEPID 2013/07375-0 and 2013/17746-5); and CNPq - the Brazilian National Counsel of Technological and Scientific Development (grant PQ 301206/2011-2). Finally, the authors are grateful for the advice of colleagues and anonymous referees used to improve this work.

References

  1. Ahmadi J, Doostparast M (2006) Bayesian estimation and prediction for some life distributions based on record values. Stat Pap 47:373–392MathSciNetCrossRefzbMATHGoogle Scholar
  2. Beaumont JP (2008) A new approach to weighting and inference in sample surveys. Biometrika 95(3):539–553MathSciNetCrossRefzbMATHGoogle Scholar
  3. Berger YG (2004) A simple variance estimator for unequal probability sampling without replacement. J Appl Stat 31:305–315MathSciNetCrossRefzbMATHGoogle Scholar
  4. Binder DA (1983) On the variances of asymptotically normal estimators from complex surveys. Int Stat Rev 51(3):279–292MathSciNetCrossRefzbMATHGoogle Scholar
  5. Cancho VG, Castro M, Rodrigues J (2012) A Bayesian analysis of the Conway–Maxwell–Poisson cure rate model. Stat Pap 53:165–176MathSciNetCrossRefzbMATHGoogle Scholar
  6. Cochran WJ (1977) Sampling techniques. Wiley, ChichesterzbMATHGoogle Scholar
  7. Congdon P (2007) Bayesian statistical modelling, 2nd edn. Wiley, ChichesterzbMATHGoogle Scholar
  8. Hajek J (1964) Asymptotic theory of rejective sampling with varying probabilities from a finite population. Ann Math Stat 35:1491–1523MathSciNetCrossRefzbMATHGoogle Scholar
  9. Horvitz DG, Thompson DJ (1952) A generalization of sampling without replacement from a finite universe. J Am Stat Assoc 47:663–685MathSciNetCrossRefzbMATHGoogle Scholar
  10. Kim C, Jung J, Chung Y (2011) Bayesian estimation for the exponentiated Weibull model under type II progressive censoring. Stat Pap 52:53–70MathSciNetCrossRefzbMATHGoogle Scholar
  11. Kim JK, Skinner CJ (2013) Weighting in survey analysis under informative sampling. Biometrika 100(2):385–398MathSciNetCrossRefzbMATHGoogle Scholar
  12. Lauretto M, Pereira CAB, Stern JM, Zacks S (2003) Full Bayesian signicance test applied to multivariate normal structure models. Braz J Prob Stat 17:147–168zbMATHGoogle Scholar
  13. Miazhynskaia T, Dorffner D (2006) A comparison of Bayesian model selection based on MCMC with an application to GARCH-type models. Stat Pap 47:525–549MathSciNetCrossRefzbMATHGoogle Scholar
  14. Pereira CAB, Stern JM (1999) Evidence and credibility: full Bayesian signicance test for precise hypotheses. Entropy 1:69–80MathSciNetCrossRefGoogle Scholar
  15. Pereira CAB, Stern JM, Wechsler S (2008) Can a significance test be genuinely Bayesian? Bayesian Anal 3(1):79–100MathSciNetCrossRefzbMATHGoogle Scholar
  16. Pfeffermann D (1993) The role of sampling weights when modeling survey data. Int Stat Rev 61(2):317–337CrossRefzbMATHGoogle Scholar
  17. Pfeffermann D (1996) The use of sampling weights for sampling data analysis. Stat Methods Med Res 5:239–261CrossRefGoogle Scholar
  18. Pfeffermann D (2011) Modelling of complex survey data: why is it a problem? how should we approach it? Surv Methodol 37(2):115–136Google Scholar
  19. Pfeffermann D, Sverchkov M (1999) Parametric and semi-parametric estimation of regression models fitted to survey data. Sankhya 61:166–186MathSciNetzbMATHGoogle Scholar
  20. Pfeffermann D, Sverchkov M (2003) Fitting generalized linear models under informative sampling. In: Skinner C, Chambers R (eds) Analysis of survey data. Wiley, New York, pp 175–196CrossRefGoogle Scholar
  21. Pfeffermann D, Krieger AM, Rinott Y (1998) Parametric distributions of complex survey data under informative probability sampling. Stat Sin 8:1087–1114MathSciNetzbMATHGoogle Scholar
  22. Pfeffermann D, Moura FAS, Silva PLM (2006) Multi-level modelling under informative sampling. Biometrica 93:943–959MathSciNetCrossRefzbMATHGoogle Scholar
  23. Rifo LLR, de Bernardini DF (2011) Full Bayesian significance test for extremal distributions. J Appl Stat 38:851–863MathSciNetCrossRefGoogle Scholar
  24. Saärndal CE, Swensson B (1987) A general view of estimation for two phases of selection with applications to two-phase sampling and nonresponse. Int Stat Rev 55:279–294MathSciNetCrossRefzbMATHGoogle Scholar
  25. Skinner CJ (1994) Sample models and weights. In Proceedings of the section on survey research methods, American Statistical Association, pp 133–142Google Scholar
  26. Skinner CJ, Holt D, Smith TMF (1989) Analysis of Complex Surveys. Wiley, ChichesterzbMATHGoogle Scholar
  27. Stern JM, Zacks S (2003) Testing the independence of poisson variates under the holgate bivariate distribution: the power of a new evidence test. Stat Probab Lett 66:313–320MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Institute of Mathematics and StatisticsUniversity of Sao Paulo (IME-USP)São PauloBrazil

Personalised recommendations