Bayesian Analysis

Posterior simulation via the signed root log-likelihood ratio

S. A. Kharroubi and T. J. Sweeting

Full-text: Open access


We explore the use of importance sampling based on signed root log-likelihood ratios for Bayesian computation. Approximations based on signed root log-likelihood ratios are used in two distinct ways; firstly, to define an importance function and, secondly, to define suitable control variates for variance reduction. These considerations give rise to alternative simulation-consistent schemes to MCMC for Bayesian computation in moderately parameterized regular problems. The schemes based on control variates can also be viewed as usefully supplementing computations based on asymptotic approximations by supplying external estimates of error. The methods are illustrated by a genetic linkage model and a censored regression model.

Article information

Bayesian Anal. Volume 5, Number 4 (2010), 787-815.

First available in Project Euclid: 19 June 2012

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Bayesian computation Control variates Importance sampling Signed root log-likelihood ratio Variance reduction


Kharroubi, S. A.; Sweeting, T. J. Posterior simulation via the signed root log-likelihood ratio. Bayesian Anal. 5 (2010), no. 4, 787--815. doi:10.1214/10-BA528.

Export citation


  • Cox, D. R. and Reid, N. (1987). Parameter orthogonality and approximate conditional inference (with discussion). J. R. Statist. Soc., B, 49, 1–39.
  • Crawford, D. E. (1970). Analysis of incomplete life test data on motorettes. Insulation Circuits, 16, 43–48.
  • DiCiccio, T. J., Field, C. A. and Fraser, D. A. S. (1990). Approximations of marginal tail probabilities and inference for scalar parameters. Biometrika, 77, 77–95.
  • DiCiccio, T. J. and Field, C. A. (1991). An accurate method for approximate conditional and Bayesian inference about linear regression models from censored data. Biometrika, 78, 903–910.
  • DiCiccio, T. J. and Martin, A. M. (1991). Approximations of marginal tail probabilities for a class of smooth functions with applications to Bayesian and conditional inference. Biometrika, 78, 891–902.
  • Evans, M. and Swartz, T. (1995a). Methods for approximating integrals in statistics with special emphasis on Bayesian integration problems. Stat. Sci., 10, 254–272.
  • Evans, M. and Swartz, T. (1995b). Bayesian integration using multivariate Student importance sampling. In Computing Science and Statistics, 27 (ed. M. M. Meyer and J. L. Rosenberger) 456–461. Interface Foundation of North America, Inc., Fairfax Station, VA.
  • Evans, M. and Swartz, T. (2000). Approximating Integrals via Monte Carlo and Deterministic Methods. Oxford: Oxford University Press.
  • Glynn, P. W. and Iglehart, D. L. (1989). Importance sampling for stochastic simulations. Management Science, 35, 1367–1392.
  • Hammersley, J. M. and Handscomb, D. C. (1964). Monte Carlo Methods. Methuen, London.
  • Hesterberg, T. (1990). Importance sampling for Bayesian estimation. Computing and Graphics in Statistics (A. Buja and P. A. Tukey, eds.) 63–75. Springer, New York.
  • Rao, C. R. (1973). Linear Statistical Inference and Applications. New York: Wiley.
  • Ripley, B. (1987). Stochastic Simulation. New York: Wiley.
  • Schmee, J. and Hahn, G. J. (1979). A simple method for regression analysis with censored data. Technometrics, 21, 417– 432.
  • Sweeting, T. J. (1984). On the choice of prior distribution for the Box-Cox transformed linear model. Biometrika, 71, 127–134.
  • Sweeting, T. J. (1992). Discussion of paper by D. A. Pierce and D. Peters. J. R. Statist. Soc., B, 54, 732–733.
  • Sweeting, T. J. (1995). A framework for Bayesian and likelihood approximations in statistics. Biometrika, 82, 1–23.
  • Sweeting, T. J. (1996). Approximate Bayesian computation based on signed roots of log-density ratios (with Discussion). Bayesian Statistics, 5, Ed. J. M. Bernardo, J. O. Berger, A. P. Dawid, and A. F. M. Smith, pp. 427–44. Oxford University Press.
  • Sweeting, T. J. and Kharroubi, S. A. (2003). Some new formulae for posterior expectations and Bartlett corrections. Test, 12, 497–521, 2003.
  • Sweeting, T. J. and Kharroubi, S. A. (2005). Application of a predictive distribution formula to Bayesian computation for incomplete data models. Statistics and Computing, 15, 167–178.
  • Tanner, M.A. and Wong, W.H. (1987). The calculation of posterior distributions by data augmentation. J. Amer. Statist. Assoc., 82, 528–540.
  • Van Dijk, H. K., Kloek, T. and Louter, A. S. (1986). An algorithm for the computation of posterior moments and densities using simple importance sampling. The Statistician, 35, 83– 90.
  • Wei, G. C. G. and Tanner, M. A. (1990). A Monte Carlo implementation of the EM algorithm and the poor man's data augmentation algorithm. J. Amer. Statist. Assoc., 85, 699–704.
  • Wolpert, R. L. (1991). Monte Carlo integration in Bayesian statistical analysis. Statistical Multiple Integration (N. Flournoy and R. K. Tsutakawa, eds.) 101–116. Amer. Math. Soc., Providence, RI. \enddescription