Statistics and Computing

, Volume 25, Issue 4, pp 809–819 | Cite as

Simulation-efficient shortest probability intervals

  • Ying Liu
  • Andrew GelmanEmail author
  • Tian Zheng


Bayesian highest posterior density (HPD) intervals can be estimated directly from simulations via empirical shortest intervals. Unfortunately, these can be noisy (that is, have a high Monte Carlo error). We derive an optimal weighting strategy using bootstrap and quadratic programming to obtain a more computationally stable HPD, or in general, shortest probability interval (Spin). We prove the consistency of our method. Simulation studies on a range of theoretical and real-data examples, some with symmetric and some with asymmetric posterior densities, show that intervals constructed using Spin have better coverage (relative to the posterior distribution) and lower Monte Carlo error than empirical shortest intervals. We implement the new method in an R package (SPIn) so it can be routinely used in post-processing of Bayesian simulations.


Bayesian computation Highest posterior density Bootstrap 



We thank Chia-Hui Huang, Daniel Lee, and Matt Hoffman for research assistance and the National Science Foundation (Grant CNS-1205516), Institute of Education Sciences (Grant DE R305D140059), and Department of Energy (Grant DE-SC0002099) for partial support of this work.


  1. Box, G.E.P., Tiao, G.C.: Bayesian Inference in Statistical Analysis. Wiley, New York (1973)zbMATHGoogle Scholar
  2. Chen, M.H., Shao, Q.M.: Monte Carlo estimation of Bayesian credible and HPD intervals. J. Comput. Gr. Stat. 8, 69–92 (1999)MathSciNetGoogle Scholar
  3. David, H.A., Nagaraja, H.N.: Order Statistics, 3rd edn. Wiley, New York (2003)zbMATHCrossRefGoogle Scholar
  4. Efron, B.: Bootstrap methods: another look at the jackknife. Ann. Stat. 7, 1–26 (1979)zbMATHMathSciNetCrossRefGoogle Scholar
  5. Gelman, A., Carlin, J.B., Stern, H.S., Rubin, D.B.: Bayesian Data Analysis. CRC Press, London (1995)Google Scholar
  6. Gelman, A., Shirley, K.: Inference from simulations and monitoring convergence. In: Brooks, S., Gelman, A., Jones, G., Meng, X.L. (eds.) Handbook of Markov Chain Monte Carlo, pp. 163–174. CRC Press, London (2011)Google Scholar
  7. R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2011)Google Scholar
  8. Rubin, D.B.: Estimation in parallel randomized experiments. J. Educ. Stat. 6, 377–401 (1981)Google Scholar
  9. Spiegelhalter, D., Thomas, A., Best, N., Gilks, W., Lunn, D.: BUGS: Bayesian Inference Using Gibbs Sampling. MRC Biostatistics Unit, Cambridge. (1994, 2002). Accessed 15 Nov 2014
  10. Stan Development Team: RStan: the R interface to Stan, Version 2.5. (2014). Accessed 15 Nov 2014
  11. van der Vaart, A.W.: Asymptotic Statistics. Cambridge University Press, Cambridge (1998)zbMATHCrossRefGoogle Scholar
  12. Zheng, T., Salganik, M.J., Gelman, A.: How many people do you know in prison?: using overdispersion in count data to estimate social structure in networks. J. Am. Stat. Assoc. 101, 409–423 (2006)zbMATHMathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Department of StatisticsColumbia UniversityNew YorkUSA
  2. 2.Google Inc.New YorkUSA

Personalised recommendations